Academic literature on the topic 'Metric Learning Approaches'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Metric Learning Approaches.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Metric Learning Approaches"
1
Sandiwarno, Sulis. "Empirical lecturers’ and students’ satisfaction assessment in e-learning systems based on the usage metrics." Research and Evaluation in Education 7, no. 2 (December 30, 2021): 118–31. http://dx.doi.org/10.21831/reid.v7i2.39642.
Full textAbstract:
Nowadays, in the pandemic of COVID-19, e-learning systems have been widely used to facilitate teaching and learning processes between lecturers and students. Assessing lecturers’ and students’ satisfaction with e-learning systems has become essential in improving the quality of education for higher learning institutions. Most existing approaches have attempted to assess users’ satisfaction based on System Usability Scale (SUS). On the other hand, different studies proposed usage-based metrics (completion rate, task duration, and mouse or cursor distance) which assess users’ satisfaction based on how they use and interact with the system. However, the cursor or mouse distance metric does not consider the effectiveness of navigation in e-learning systems, and such approaches measure either lecturers’ or students’ satisfaction independently. Towards this end, we propose a lostness metric to replace the click or cursor distance metric for assessing lecturers’ and students’ satisfaction with using e-learning systems. Furthermore, to obtain a deep analysis of users’ satisfaction, we tandem the usage-based metric (i.e., completion rate, task duration, and lostness) and the SUS metric. The evaluation results indicate that the proposed approach can precisely predict users’ satisfaction with e-learning systems.
2
Li, Zilong. "A Boosting-Based Deep Distance Metric Learning Method." Computational Intelligence and Neuroscience 2022 (March 15, 2022): 1–9. http://dx.doi.org/10.1155/2022/2665843.
Full textAbstract:
By leveraging neural networks, deep distance metric learning has yielded impressive results in computer vision applications. However, the existing approaches mostly focus a single deep distance metric based on pairs or triplets of samples. It is difficult for them to handle heterogeneous data and avoid overfitting. This study proposes a boosting-based learning method of multiple deep distance metrics, which generates the final distance metric through iterative training of multiple weak distance metrics. Firstly, the distance of sample pairs was mapped by a convolution neural network (CNN) and evaluated by a piecewise linear function. Secondly, the evaluation function was added as a weak learner to the boosting algorithm to generate a strong learner. Each weak learner targets the difficult samples different from the samples of previous learners. Next, an alternating optimization method was employed to train the network and loss function. Finally, the effectiveness of our method was demonstrated in contrast to state of the arts on retrieving the images from the CUB-200-2011, Cars-196, and Stanford Online Products (SOP) datasets.
3
Dutta, Ujjal Kr, Mehrtash Harandi, and C. Chandra Sekhar. "Unsupervised Metric Learning with Synthetic Examples." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 3834–41. http://dx.doi.org/10.1609/aaai.v34i04.5795.
Full textAbstract:
Distance Metric Learning (DML) involves learning an embedding that brings similar examples closer while moving away dissimilar ones. Existing DML approaches make use of class labels to generate constraints for metric learning. In this paper, we address the less-studied problem of learning a metric in an unsupervised manner. We do not make use of class labels, but use unlabeled data to generate adversarial, synthetic constraints for learning a metric inducing embedding. Being a measure of uncertainty, we minimize the entropy of a conditional probability to learn the metric. Our stochastic formulation scales well to large datasets, and performs competitive to existing metric learning methods.
4
Yang, Lu, Peng Wang, and Yanning Zhang. "Stop-Gradient Softmax Loss for Deep Metric Learning." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 3 (June 26, 2023): 3164–72. http://dx.doi.org/10.1609/aaai.v37i3.25421.
Full textAbstract:
Deep metric learning aims to learn a feature space that models the similarity between images, and feature normalization is a critical step for boosting performance. However directly optimizing L2-normalized softmax loss cause the network to fail to converge. Therefore some SOTA approaches appends a scale layer after the inner product to relieve the convergence problem, but it incurs a new problem that it's difficult to learn the best scaling parameters. In this letter, we look into the characteristic of softmax-based approaches and propose a novel learning objective function Stop-Gradient Softmax Loss (SGSL) to solve the convergence problem in softmax-based deep metric learning with L2-normalization. In addition, we found a useful trick named Remove the last BN-ReLU (RBR). It removes the last BN-ReLU in the backbone to reduce the learning burden of the model. Experimental results on four fine-grained image retrieval benchmarks show that our proposed approach outperforms most existing approaches, i.e., our approach achieves 75.9% on CUB-200-2011, 94.7% on CARS196 and 83.1% on SOP which outperforms other approaches at least 1.7%, 2.9% and 1.7% on Recall@1.
5
Dutta, Ujjal Kr, Mehrtash Harandi, and C. Chandra Shekhar. "Semi-Supervised Metric Learning: A Deep Resurrection." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 8 (May 18, 2021): 7279–87. http://dx.doi.org/10.1609/aaai.v35i8.16894.
Full textAbstract:
Distance Metric Learning (DML) seeks to learn a discriminative embedding where similar examples are closer, and dissimilar examples are apart. In this paper, we address the problem of Semi-Supervised DML (SSDML) that tries to learn a metric using a few labeled examples, and abundantly available unlabeled examples. SSDML is important because it is infeasible to manually annotate all the examples present in a large dataset. Surprisingly, with the exception of a few classical approaches that learn a linear Mahalanobis metric, SSDML has not been studied in the recent years, and lacks approaches in the deep SSDML scenario. In this paper, we address this challenging problem, and revamp SSDML with respect to deep learning. In particular, we propose a stochastic, graph-based approach that first propagates the affinities between the pairs of examples from labeled data, to that of the unlabeled pairs. The propagated affinities are used to mine triplet based constraints for metric learning. We impose orthogonality constraint on the metric parameters, as it leads to a better performance by avoiding a model collapse.
6
Kaya and Bilge. "Deep Metric Learning: A Survey." Symmetry 11, no. 9 (August 21, 2019): 1066. http://dx.doi.org/10.3390/sym11091066.
Full textAbstract:
Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.
7
Syed, Muhamamd Adnan, Zhenjun Han, Zhaoju Li, and Jianbin Jiao. "Impostor Resilient Multimodal Metric Learning for Person Reidentification." Advances in Multimedia 2018 (2018): 1–11. http://dx.doi.org/10.1155/2018/3202495.
Full textAbstract:
In person reidentification distance metric learning suffers a great challenge from impostor persons. Mostly, distance metrics are learned by maximizing the similarity between positive pair against impostors that lie on different transform modals. In addition, these impostors are obtained from Gallery view for query sample only, while the Gallery sample is totally ignored. In real world, a given pair of query and Gallery experience different changes in pose, viewpoint, and lighting. Thus, impostors only from Gallery view can not optimally maximize their similarity. Therefore, to resolve these issues we have proposed an impostor resilient multimodal metric (IRM3). IRM3 is learned for each modal transform in the image space and uses impostors from both Probe and Gallery views to effectively restrict large number of impostors. Learned IRM3 is then evaluated on three benchmark datasets, VIPeR, CUHK01, and CUHK03, and shows significant improvement in performance compared to many previous approaches.
8
Saha, Soumadeep, Utpal Garain, Arijit Ukil, Arpan Pal, and Sundeep Khandelwal. "MedTric : A clinically applicable metric for evaluation of multi-label computational diagnostic systems." PLOS ONE 18, no. 8 (August 10, 2023): e0283895. http://dx.doi.org/10.1371/journal.pone.0283895.
Full textAbstract:
When judging the quality of a computational system for a pathological screening task, several factors seem to be important, like sensitivity, specificity, accuracy, etc. With machine learning based approaches showing promise in the multi-label paradigm, they are being widely adopted to diagnostics and digital therapeutics. Metrics are usually borrowed from machine learning literature, and the current consensus is to report results on a diverse set of metrics. It is infeasible to compare efficacy of computational systems which have been evaluated on different sets of metrics. From a diagnostic utility standpoint, the current metrics themselves are far from perfect, often biased by prevalence of negative samples or other statistical factors and importantly, they are designed to evaluate general purpose machine learning tasks. In this paper we outline the various parameters that are important in constructing a clinical metric aligned with diagnostic practice, and demonstrate their incompatibility with existing metrics. We propose a new metric, MedTric that takes into account several factors that are of clinical importance. MedTric is built from the ground up keeping in mind the unique context of computational diagnostics and the principle of risk minimization, penalizing missed diagnosis more harshly than over-diagnosis. MedTric is a unified metric for medical or pathological screening system evaluation. We compare this metric against other widely used metrics and demonstrate how our system outperforms them in key areas of medical relevance.
9
Bhukar, Karan, Harshit Kumar, Dinesh Raghu, and Ajay Gupta. "End-to-End Deep Reinforcement Learning for Conversation Disentanglement." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 11 (June 26, 2023): 12571–79. http://dx.doi.org/10.1609/aaai.v37i11.26480.
Full textAbstract:
Collaborative Communication platforms (e.g., Slack) support multi-party conversations which contain a large number of messages on shared channels. Multiple conversations intermingle within these messages. The task of conversation disentanglement is to cluster these intermingled messages into conversations. Existing approaches are trained using loss functions that optimize only local decisions, i.e. predicting reply-to links for each message and thereby creating clusters of conversations. In this work, we propose an end-to-end reinforcement learning (RL) approach that directly optimizes a global metric. We observe that using existing global metrics such as variation of information and adjusted rand index as a reward for the RL agent deteriorates its performance. This behaviour is because these metrics completely ignore the reply-to links between messages (local decisions) during reward computation. Therefore, we propose a novel thread-level reward function that captures the global metric without ignoring the local decisions. Through experiments on the Ubuntu IRC dataset, we demonstrate that the proposed RL model improves the performance on both link-level and conversation-level metrics.
10
Komamizu, Takahiro. "Combining Multi-ratio Undersampling and Metric Learning for Imbalanced Classification." Journal of Data Intelligence 2, no. 4 (December 2021): 462–75. http://dx.doi.org/10.26421/jdi2.4-5.
Full textAbstract:
In classification, class imbalance is a factor that degrades the classification performance of many classification methods. Resampling is one widely accepted approach to the class imbalance; however, it still suffers from an insufficient data space, which also degrades performance. To overcome this, in this paper, an undersampling-based imbalanced classification framework, MMEnsemble, is proposed that incorporates metric learning into a multi-ratio undersampling-based ensemble. This framework also overcomes a problem with determining the appropriate sampling ratio in the multi-ratio ensemble method. It was evaluated by using 12 real-world datasets. It outperformed the state-of-the-art approaches of metric learning, undersampling, and oversampling in recall and ROC-AUC, and it performed comparably with them in terms of Gmean and F-measure metrics.
Dissertations / Theses on the topic "Metric Learning Approaches"
1
Abou-Moustafa, Karim. "Metric learning revisited: new approaches for supervised and unsupervised metric learning with analysis and algorithms." Thesis, McGill University, 2012. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=106370.
Full textAbstract:
In machine learning one is usually given a data set of real high dimensional vectors X, based on which it is desired to select a hypothesis θ from the space of hypotheses Θ using a learning algorithm. An immediate assumption that is usually imposed on X is that it is a subset from the very general embedding space Rp which makes the Euclidean distance ∥•∥2 to become the default metric for the elements of X. Since various learning algorithms assume that the input space is Rp with its endowed metric ∥•∥2 as a (dis)similarity measure, it follows that selecting hypothesis θ becomes intrinsically tied to the Euclidean distance. Metric learning is the problem of selecting a specific metric dX from a certain family of metrics D based on the properties of the elements in the set X. Under some performance measure, the metric dX is expected to perform better on X than any other metric d 2 D. If the learning algorithm replaces the very general metric ∥•∥2 with the metric dX , then selecting hypothesis θ will be tied to the more specific metric dX which carries all the information on the properties of the elements in X. In this thesis I propose two algorithms for learning the metric dX ; the first for supervised learning settings, and the second for unsupervised, as well as for supervised and semi-supervised settings. In particular, I propose algorithms that take into consideration the structure and geometry of X on one hand, and the characteristics of real world data sets on the other. However, if we are also seeking dimensionality reduction, then under some mild assumptions on the topology of X, and based on the available a priori information, one can learn an embedding for X into a low dimensional Euclidean space Rp0, p0 << p, where the Euclidean distance better reveals the similarities between the elements of X and their groupings (clusters). That is, as a by-product, we obtain dimensionality reduction together with metric learning. In the supervised setting, I propose PARDA, or Pareto discriminant analysis for discriminative linear dimensionality reduction. PARDA is based on the machinery of multi-objective optimization; simultaneously optimizing multiple, possibly conflicting, objective functions. This allows PARDA to adapt to the class topology in the lower dimensional space, and naturally handles the class masking problem that is inherent in Fisher's discriminant analysis framework for multiclass problems. As a result, PARDA yields significantly better classification results when compared with modern techniques for discriminative dimensionality reduction. In the unsupervised setting, I propose an algorithmic framework, denoted by ?? (note the different notation), that encapsulates spectral manifold learning algorithms and gears them for metric learning. The framework ?? captures the local structure and the local density information from each point in a data set, and hence it carries all the information on the varying sample density in the input space. The structure of ?? induces two distance metrics for its elements, the Bhattacharyya-Riemann metric dBR and the Jeffreys-Riemann metric dJR. Both metrics reorganize the proximity between the points in X based on the local structure and density around each point. As a result, when combining the metric space (??, dBR) or (??, dJR) with spectral clustering and Euclidean embedding, they yield significant improvements in clustering accuracies and error rates for a large variety of clustering and classification tasks.Dans cette thèse, je propose deux algorithmes pour l'apprentissage de la métrique dX; le premier pour l'apprentissage supervisé, et le deuxième pour l'apprentissage non-supervisé, ainsi que pour l'apprentissage supervisé et semi-supervisé. En particulier, je propose des algorithmes qui prennent en considération la structure et la géométrie de X d'une part, et les caractéristiques des ensembles de données du monde réel d'autre part. Cependant, si on cherche également la réduction de dimension, donc sous certaines hypothèses légères sur la topologie de X, et en même temps basé sur des informations disponibles a priori, on peut apprendre une intégration de X dans un espace Euclidien de petite dimension Rp0 p0 << p, où la distance Euclidienne révèle mieux les ressemblances entre les éléments de X et leurs groupements (clusters). Alors, comme un sous-produit, on obtient simultanément une réduction de dimension et un apprentissage métrique. Pour l'apprentissage supervisé, je propose PARDA, ou Pareto discriminant analysis, pour la discriminante réduction linéaire de dimension. PARDA est basé sur le mécanisme d'optimisation à multi-objectifs; optimisant simultanément plusieurs fonctions objectives, éventuellement des fonctions contradictoires. Cela permet à PARDA de s'adapter à la topologie de classe dans un espace dimensionnel plus petit, et naturellement gère le problème de masquage de classe associé au discriminant Fisher dans le cadre d'analyse de problèmes à multi-classes. En conséquence, PARDA permet des meilleurs résultats de classification par rapport aux techniques modernes de réduction discriminante de dimension. Pour l'apprentissage non-supervisés, je propose un cadre algorithmique, noté par ??, qui encapsule les algorithmes spectraux d'apprentissage formant an algorithme d'apprentissage de métrique. Le cadre ?? capture la structure locale et la densité locale d'information de chaque point dans un ensemble de données, et donc il porte toutes les informations sur la densité d'échantillon différente dans l'espace d'entrée. La structure de ?? induit deux métriques de distance pour ses éléments: la métrique Bhattacharyya-Riemann dBR et la métrique Jeffreys-Riemann dJR. Les deux mesures réorganisent la proximité entre les points de X basé sur la structure locale et la densité autour de chaque point. En conséquence, lorsqu'on combine l'espace métrique (??, dBR) ou (??, dJR) avec les algorithmes de "spectral clustering" et "Euclidean embedding", ils donnent des améliorations significatives dans les précisions de regroupement et les taux d'erreur pour une grande variété de tâches de clustering et de classification.
2
Zheng, Lilei. "Triangular similarity metric learning : A siamese architecture approach." Thesis, Lyon, 2016. http://www.theses.fr/2016LYSEI045/document.
Full textAbstract:
Dans de nombreux problèmes d’apprentissage automatique et de reconnaissance des formes, il y a toujours un besoin de fonctions métriques appropriées pour mesurer la distance ou la similarité entre des données. La fonction métrique est une fonction qui définit une distance ou une similarité entre chaque paire d’éléments d’un ensemble de données. Dans cette thèse, nous proposons une nouvelle methode, Triangular Similarity Metric Learning (TSML), pour spécifier une fonction métrique de données automatiquement. Le système TSML proposée repose une architecture Siamese qui se compose de deux sous-systèmes identiques partageant le même ensemble de paramètres. Chaque sous-système traite un seul échantillon de données et donc le système entier reçoit une paire de données en entrée. Le système TSML comprend une fonction de coût qui définit la relation entre chaque paire de données et une fonction de projection permettant l’apprentissage des formes de haut niveau. Pour la fonction de coût, nous proposons d’abord la similarité triangulaire (Triangular Similarity), une nouvelle similarité métrique qui équivaut à la similarité cosinus. Sur la base d’une version simplifiée de la similarité triangulaire, nous proposons la fonction triangulaire (the triangular loss) afin d’effectuer l’apprentissage de métrique, en augmentant la similarité entre deux vecteurs dans la même classe et en diminuant la similarité entre deux vecteurs de classes différentes. Par rapport aux autres distances ou similarités, la fonction triangulaire et sa fonction gradient nous offrent naturellement une interprétation géométrique intuitive et intéressante qui explicite l’objectif d’apprentissage de métrique. En ce qui concerne la fonction de projection, nous présentons trois fonctions différentes: une projection linéaire qui est réalisée par une matrice simple, une projection non-linéaire qui est réalisée par Multi-layer Perceptrons (MLP) et une projection non-linéaire profonde qui est réalisée par Convolutional Neural Networks (CNN). Avec ces fonctions de projection, nous proposons trois systèmes de TSML pour plusieurs applications: la vérification par paires, l’identification d’objet, la réduction de la dimensionnalité et la visualisation de données. Pour chaque application, nous présentons des expérimentations détaillées sur des ensembles de données de référence afin de démontrer l’efficacité de notre systèmes de TSMLIn many machine learning and pattern recognition tasks, there is always a need for appropriate metric functions to measure pairwise distance or similarity between data, where a metric function is a function that defines a distance or similarity between each pair of elements of a set. In this thesis, we propose Triangular Similarity Metric Learning (TSML) for automatically specifying a metric from data. A TSML system is loaded in a siamese architecture which consists of two identical sub-systems sharing the same set of parameters. Each sub-system processes a single data sample and thus the whole system receives a pair of data as the input. The TSML system includes a cost function parameterizing the pairwise relationship between data and a mapping function allowing the system to learn high-level features from the training data. In terms of the cost function, we first propose the Triangular Similarity, a novel similarity metric which is equivalent to the well-known Cosine Similarity in measuring a data pair. Based on a simplified version of the Triangular Similarity, we further develop the triangular loss function in order to perform metric learning, i.e. to increase the similarity between two vectors in the same class and to decrease the similarity between two vectors of different classes. Compared with other distance or similarity metrics, the triangular loss and its gradient naturally offer us an intuitive and interesting geometrical interpretation of the metric learning objective. In terms of the mapping function, we introduce three different options: a linear mapping realized by a simple transformation matrix, a nonlinear mapping realized by Multi-layer Perceptrons (MLP) and a deep nonlinear mapping realized by Convolutional Neural Networks (CNN). With these mapping functions, we present three different TSML systems for various applications, namely, pairwise verification, object identification, dimensionality reduction and data visualization. For each application, we carry out extensive experiments on popular benchmarks and datasets to demonstrate the effectiveness of the proposed systems
3
Rossi, Alex. "Self-supervised information retrieval: a novel approach based on Deep Metric Learning and Neural Language Models." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Find full textAbstract:
Most of the existing open-source search engines, utilize keyword or tf-idf based techniques to find relevant documents and web pages relative to an input query. Although these methods, with the help of a page rank or knowledge graphs, proved to be effective in some cases, they often fail to retrieve relevant instances for more complicated queries that would require a semantic understanding to be exploited.
In this Thesis, a self-supervised information retrieval system based on transformers is employed to build a semantic search engine over the library of Gruppo Maggioli company. Semantic search or search with meaning can refer to an understanding of the query, instead of simply finding words matches and, in general, it represents knowledge in a way suitable for retrieval.
We chose to investigate a new self-supervised strategy to handle the training of unlabeled data based on the creation of pairs of ’artificial’ queries and the respective positive passages. We claim that by removing the reliance on labeled data, we may use the large volume of unlabeled material on the web without being limited to languages or domains where labeled data is abundant.
4
Dahab, Sarah. "An approach to measuring software systems using new combined metrics of complex test." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLL015/document.
Full textAbstract:
La plupart des métriques de qualité logicielle mesurables sont actuellement basées sur des mesures bas niveau, telles que la complexité cyclomatique, le nombre de lignes de commentaires ou le nombre de blocs dupliqués. De même, la qualité de l'ingénierie logicielle est davantage liée à des facteurs techniques ou de gestion, et devrait fournir des indicateurs utiles pour les exigences de qualité. Actuellement, l'évaluation de ces exigences de qualité n'est pas automatisée, elle n'est pas validée empiriquement dans des contextes réels et l'évaluation est définie sans tenir compte des principes de la théorie de la mesure. Par conséquent, il est difficile de comprendre où et comment améliorer le logiciel suivant le résultat obtenu. Dans ce domaine, les principaux défis consistent à définir des métriques adéquates et utiles pour les exigences de qualité, les documents de conception de logiciels et autres artefacts logiciels, y compris les activités de test.Les principales problématiques scientifiques abordées dans cette thèse sont les suivantes: définir des mesures et des outils de support pour mesurer les activités d'ingénierie logicielle modernes en termes d'efficacité et de qualité. La seconde consiste à analyser les résultats de mesure pour identifier quoi et comment s'améliorer automatiquement. Le dernier consiste en l'automatisation du processus de mesure afin de réduire le temps de développement. Une telle solution hautement automatisée et facile à déployer constituera une solution révolutionnaire, car les outils actuels ne le prennent pas en charge, sauf pour une portée très limitéeMost of the measurable software quality metrics are currently based on low level metrics, such as cyclomatic complexity, number of comment lines or number of duplicated blocks. Likewise, quality of software engineering is more related to technical or management factoid, and should provide useful metrics for quality requirements. Currently the assessment of these quality requirements is not automated, not empirically validated in real contexts, and the assessment is defined without considering principles of measurement theory. Therefore it is difficult to understand where and how to improve the software following the obtained result. In this domain, the main challenges are to define adequate and useful metrics for quality requirements, software design documents and other software artifacts, including testing activities.The main scientific problematic that are tackled in this proposed thesis are the following : defining metrics and its supporting tools for measuring modern software engineering activities with respect to efficiency and quality. The second consists in analyzing measurement results for identifying what and how to improve automatically. The last one consists in the measurement process automation in order to reduce the development time. Such highly automated and easy to deploy solution will be a breakthrough solution, as current tools do not support it except for very limited scope
5
Rydell, Christopher. "Deep Learning for Whole Slide Image Cytology : A Human-in-the-Loop Approach." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-450356.
Full textAbstract:
With cancer being one of the leading causes of death globally, and with oral cancers being among the most common types of cancer, it is of interest to conduct large-scale oral cancer screening among the general population. Deep Learning can be used to make this possible despite the medical expertise required for early detection of oral cancers. A bottleneck of Deep Learning is the large amount of data required to train a good model. This project investigates two topics: certainty calibration, which aims to make a machine learning model produce more reliable predictions, and Active Learning, which aims to reduce the amount of data that needs to be labeled for Deep Learning to be effective. In the investigation of certainty calibration, five different methods are compared, and the best method is found to be Dirichlet calibration. The Active Learning investigation studies a single method, Cost-Effective Active Learning, but it is found to produce poor results with the given experiment setting. These two topics inspire the further development of the cytological annotation tool CytoBrowser, which is designed with oral cancer data labeling in mind. The proposedevolution integrates into the existing tool a Deep Learning-assisted annotation workflow that supports multiple users.
6
Ghadie, Mohamed A. "Analysis and Reconstruction of the Hematopoietic Stem Cell Differentiation Tree: A Linear Programming Approach for Gene Selection." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/32048.
Full textAbstract:
Stem cells differentiate through an organized hierarchy of intermediate cell types to terminally differentiated cell types. This process is largely guided by master transcriptional regulators, but it also depends on the expression of many other types of genes. The discrete cell types in the differentiation hierarchy are often identified based on the expression or non-expression of certain marker genes. Historically, these have often been various cell-surface proteins, which are fairly easy to assay biochemically but are not necessarily causative of the cell type, in the sense of being master transcriptional regulators. This raises important questions about how gene expression across the whole genome controls or reflects cell state, and in particular, differentiation hierarchies. Traditional approaches to understanding gene expression patterns across multiple conditions, such as principal components analysis or K-means clustering, can group cell types based on gene expression, but they do so without knowledge of the differentiation hierarchy. Hierarchical clustering and maximization of parsimony can organize the cell types into a tree, but in general this tree is different from the differentiation hierarchy. Using hematopoietic differentiation as an example, we demonstrate how many genes other than marker genes are able to discriminate between different branches of the differentiation tree by proposing two models for detecting genes that are up-regulated or down-regulated in distinct lineages. We then propose a novel approach to solving the following problem: Given the differentiation hierarchy and gene expression data at each node, construct a weighted Euclidean distance metric such that the minimum spanning tree with respect to that metric is precisely the given differentiation hierarchy. We provide a set of linear constraints that are provably sufficient for the desired construction and a linear programming framework to identify sparse sets of weights, effectively identifying genes that are most relevant for discriminating different parts of the tree. We apply our method to microarray gene expression data describing 38 cell types in the hematopoiesis hierarchy, constructing a sparse weighted Euclidean metric that uses just 175 genes. These 175 genes are different than the marker genes that were used to identify the 38 cell types, hence offering a novel alternative way of discriminating different branches of the tree. A DAVID functional annotation analysis shows that the 175 genes reflect major processes and pathways active in different parts of the tree. However, we find that there are many alternative sets of weights that satisfy the linear constraints. Thus, in the style of random-forest training, we also construct metrics based on random subsets of the genes and compare them to the metric of 175 genes. Our results show that the 175 genes frequently appear in the random metrics, implicating their significance from an empirical point of view as well. Finally, we show how our linear programming method is able to identify columns that were selected to build minimum spanning trees on the nodes of random variable-size matrices.
7
NOTARANGELO, NICLA MARIA. "A Deep Learning approach for monitoring severe rainfall in urban catchments using consumer cameras. Models development and deployment on a case study in Matera (Italy) Un approccio basato sul Deep Learning per monitorare le piogge intense nei bacini urbani utilizzando fotocamere generiche. Sviluppo e implementazione di modelli su un caso di studio a Matera (Italia)." Doctoral thesis, Università degli studi della Basilicata, 2021. http://hdl.handle.net/11563/147016.
Full textAbstract:
In the last 50 years, flooding has figured as the most frequent and widespread natural disaster globally. Extreme precipitation events stemming from climate change could alter the hydro-geological regime resulting in increased flood risk. Near real-time precipitation monitoring at local scale is essential for flood risk mitigation in urban and suburban areas, due to their high vulnerability. Presently, most of the rainfall data is obtained from ground‐based measurements or remote sensing that provide limited information in terms of temporal or spatial resolution. Other problems may be due to the high costs. Furthermore, rain gauges are unevenly spread and usually placed away from urban centers. In this context, a big potential is represented by the use of innovative techniques to develop low-cost monitoring systems. Despite the diversity of purposes, methods and epistemological fields, the literature on the visual effects of the rain supports the idea of camera-based rain sensors but tends to be device-specific. The present thesis aims to investigate the use of easily available photographing devices as rain detectors-gauges to develop a dense network of low-cost rainfall sensors to support the traditional methods with an expeditious solution embeddable into smart devices. As opposed to existing works, the study focuses on maximizing the number of image sources (like smartphones, general-purpose surveillance cameras, dashboard cameras, webcams, digital cameras, etc.). This encompasses cases where it is not possible to adjust the camera parameters or obtain shots in timelines or videos. Using a Deep Learning approach, the rainfall characterization can be achieved through the analysis of the perceptual aspects that determine whether and how a photograph represents a rainy condition. The first scenario of interest for the supervised learning was a binary classification; the binary output (presence or absence of rain) allows the detection of the presence of precipitation: the cameras act as rain detectors. Similarly, the second scenario of interest was a multi-class classification; the multi-class output described a range of quasi-instantaneous rainfall intensity: the cameras act as rain estimators. Using Transfer Learning with Convolutional Neural Networks, the developed models were compiled, trained, validated, and tested. The preparation of the classifiers included the preparation of a suitable dataset encompassing unconstrained verisimilar settings: open data, several data owned by National Research Institute for Earth Science and Disaster Prevention - NIED (dashboard cameras in Japan coupled with high precision multi-parameter radar data), and experimental activities conducted in the NIED Large Scale Rainfall Simulator. The outcomes were applied to a real-world scenario, with the experimentation through a pre-existent surveillance camera using 5G connectivity provided by Telecom Italia S.p.A. in the city of Matera (Italy). Analysis unfolded on several levels providing an overview of generic issues relating to the urban flood risk paradigm and specific territorial questions inherent with the case study. These include the context aspects, the important role of rainfall from driving the millennial urban evolution to determining present criticality, and components of a Web prototype for flood risk communication at local scale. The results and the model deployment raise the possibility that low‐cost technologies and local capacities can help to retrieve rainfall information for flood early warning systems based on the identification of a significant meteorological state. The binary model reached accuracy and F1 score values of 85.28% and 0.86 for the test, and 83.35% and 0.82 for the deployment. The multi-class model reached test average accuracy and macro-averaged F1 score values of 77.71% and 0.73 for the 6-way classifier, and 78.05% and 0.81 for the 5-class. The best performances were obtained in heavy rainfall and no-rain conditions, whereas the mispredictions are related to less severe precipitation. The proposed method has limited operational requirements, can be easily and quickly implemented in real use cases, exploiting pre-existent devices with a parsimonious use of economic and computational resources. The classification can be performed on single photographs taken in disparate conditions by commonly used acquisition devices, i.e. by static or moving cameras without adjusted parameters. This approach is especially useful in urban areas where measurement methods such as rain gauges encounter installation difficulties or operational limitations or in contexts where there is no availability of remote sensing data. The system does not suit scenes that are also misleading for human visual perception. The approximations inherent in the output are acknowledged. Additional data may be gathered to address gaps that are apparent and improve the accuracy of the precipitation intensity prediction. Future research might explore the integration with further experiments and crowdsourced data, to promote communication, participation, and dialogue among stakeholders and to increase public awareness, emergency response, and civic engagement through the smart community idea.Negli ultimi 50 anni, le alluvioni si sono confermate come il disastro naturale più frequente e diffuso a livello globale. Tra gli impatti degli eventi meteorologici estremi, conseguenti ai cambiamenti climatici, rientrano le alterazioni del regime idrogeologico con conseguente incremento del rischio alluvionale. Il monitoraggio delle precipitazioni in tempo quasi reale su scala locale è essenziale per la mitigazione del rischio di alluvione in ambito urbano e periurbano, aree connotate da un'elevata vulnerabilità. Attualmente, la maggior parte dei dati sulle precipitazioni è ottenuta da misurazioni a terra o telerilevamento che forniscono informazioni limitate in termini di risoluzione temporale o spaziale. Ulteriori problemi possono derivare dagli elevati costi. Inoltre i pluviometri sono distribuiti in modo non uniforme e spesso posizionati piuttosto lontano dai centri urbani, comportando criticità e discontinuità nel monitoraggio. In questo contesto, un grande potenziale è rappresentato dall'utilizzo di tecniche innovative per sviluppare sistemi inediti di monitoraggio a basso costo. Nonostante la diversità di scopi, metodi e campi epistemologici, la letteratura sugli effetti visivi della pioggia supporta l'idea di sensori di pioggia basati su telecamera, ma tende ad essere specifica per dispositivo scelto. La presente tesi punta a indagare l'uso di dispositivi fotografici facilmente reperibili come rilevatori-misuratori di pioggia, per sviluppare una fitta rete di sensori a basso costo a supporto dei metodi tradizionali con una soluzione rapida incorporabile in dispositivi intelligenti. A differenza dei lavori esistenti, lo studio si concentra sulla massimizzazione del numero di fonti di immagini (smartphone, telecamere di sorveglianza generiche, telecamere da cruscotto, webcam, telecamere digitali, ecc.). Ciò comprende casi in cui non sia possibile regolare i parametri fotografici o ottenere scatti in timeline o video. Utilizzando un approccio di Deep Learning, la caratterizzazione delle precipitazioni può essere ottenuta attraverso l'analisi degli aspetti percettivi che determinano se e come una fotografia rappresenti una condizione di pioggia. Il primo scenario di interesse per l'apprendimento supervisionato è una classificazione binaria; l'output binario (presenza o assenza di pioggia) consente la rilevazione della presenza di precipitazione: gli apparecchi fotografici fungono da rivelatori di pioggia. Analogamente, il secondo scenario di interesse è una classificazione multi-classe; l'output multi-classe descrive un intervallo di intensità delle precipitazioni quasi istantanee: le fotocamere fungono da misuratori di pioggia. Utilizzando tecniche di Transfer Learning con reti neurali convoluzionali, i modelli sviluppati sono stati compilati, addestrati, convalidati e testati. La preparazione dei classificatori ha incluso la preparazione di un set di dati adeguato con impostazioni verosimili e non vincolate: dati aperti, diversi dati di proprietà del National Research Institute for Earth Science and Disaster Prevention - NIED (telecamere dashboard in Giappone accoppiate con dati radar multiparametrici ad alta precisione) e attività sperimentali condotte nel simulatore di pioggia su larga scala del NIED. I risultati sono stati applicati a uno scenario reale, con la sperimentazione attraverso una telecamera di sorveglianza preesistente che utilizza la connettività 5G fornita da Telecom Italia S.p.A. nella città di Matera (Italia). L'analisi si è svolta su più livelli, fornendo una panoramica sulle questioni relative al paradigma del rischio di alluvione in ambito urbano e questioni territoriali specifiche inerenti al caso di studio. Queste ultime includono diversi aspetti del contesto, l'importante ruolo delle piogge dal guidare l'evoluzione millenaria della morfologia urbana alla determinazione delle criticità attuali, oltre ad alcune componenti di un prototipo Web per la comunicazione del rischio alluvionale su scala locale. I risultati ottenuti e l'implementazione del modello corroborano la possibilità che le tecnologie a basso costo e le capacità locali possano aiutare a caratterizzare la forzante pluviometrica a supporto dei sistemi di allerta precoce basati sull'identificazione di uno stato meteorologico significativo. Il modello binario ha raggiunto un'accuratezza e un F1-score di 85,28% e 0,86 per il set di test e di 83,35% e 0,82 per l'implementazione nel caso di studio. Il modello multi-classe ha raggiunto un'accuratezza media e F1-score medio (macro-average) di 77,71% e 0,73 per il classificatore a 6 vie e 78,05% e 0,81 per quello a 5 classi. Le prestazioni migliori sono state ottenute nelle classi relative a forti precipitazioni e assenza di pioggia, mentre le previsioni errate sono legate a precipitazioni meno estreme. Il metodo proposto richiede requisiti operativi limitati, può essere implementato facilmente e rapidamente in casi d'uso reali, sfruttando dispositivi preesistenti con un uso parsimonioso di risorse economiche e computazionali. La classificazione può essere eseguita su singole fotografie scattate in condizioni disparate da dispositivi di acquisizione di uso comune, ovvero da telecamere statiche o in movimento senza regolazione dei parametri. Questo approccio potrebbe essere particolarmente utile nelle aree urbane in cui i metodi di misurazione come i pluviometri incontrano difficoltà di installazione o limitazioni operative o in contesti in cui non sono disponibili dati di telerilevamento o radar. Il sistema non si adatta a scene che sono fuorvianti anche per la percezione visiva umana. I limiti attuali risiedono nelle approssimazioni intrinseche negli output. Per colmare le lacune evidenti e migliorare l'accuratezza della previsione dell'intensità di precipitazione, sarebbe possibile un'ulteriore raccolta di dati. Sviluppi futuri potrebbero riguardare l'integrazione con ulteriori esperimenti in campo e dati da crowdsourcing, per promuovere comunicazione, partecipazione e dialogo aumentando la resilienza attraverso consapevolezza pubblica e impegno civico in una concezione di comunità smart.
8
Kim, Junae. "Efficient and scalable approaches to Mahalanobis distance metric learning." Phd thesis, 2012. http://hdl.handle.net/1885/151771.
Full textAbstract:
The development of an appropriate data-dependent distance metric is a compelling goal for many visual recognition tasks. This thesis proposes three efficient and scalable distance learning algorithms by employing the principle of margin maximization to secure better generalization performances. The proposed algorithms formulate metric learning as a convex optimization problem with a positive semidefinite (psd) matrix variable. A standard interior-point semidefinite programming (SDP) solver has a complexity of O(n to the power of 6.5) where n is the number of variables, and can only solve problems with up to a few thousand variables. Since the number of variables is D ( D+1 ) / 2, where D is the dimensionality of the input data, this corresponds to a limit of around D < 100. This high complexity hampers the application of metric learning to high-dimensional problems. Compared with conventional methods such as standard interior-point algorithms or the special solver used in the large-margin nearest neighbor (LMNN), our algorithms are much more efficient and perform better in terms of scalability. The first algorithm, SDPmetric is based on an important theorem in which a psd matrix with a trace of one can always be represented as a convex combination of multiple rank-one matrices. The algorithm not only naturally maintains the psd requirement of the matrix variable that is essential for metric learning but also significantly cuts down the computational overhead, making it much more efficient with increasing the dimensions of feature vectors. In brief, only the leading eigendecomposition is required for metric learning; hence, the time complexity is O ( t times D squared ) , where t is the number of iterations and D is the dimensionality of the feature vectors. The second algorithm, BoostMetric is based on a boosting technique to learn the Mahalanobis distance metric. One of the primary difficulties in learning this metric is ensuring that the Mahalanobis matrix remains psd. SDP is sometimes used to enforce this constraint but does not scale well. Similar to SDPMetric, BoostMetric is instead based on a key observation that any psd matrix can be decomposed into a linear positive combination of trace-one rank-one matrices. BoostMetric thus uses rank-one psd matrices as weak learners within an efficient and scalable boosting-based learning process. The resulting method is easy to implement, does not require tuning, and can accommodate various types of constraints. The last algorithm, FrobMetric is designed for a very efficient approach to this metric learning problem. A Lagrange dual approach is formulated that is much simpler to optimize and we therefore be used to solve much larger Mahalanobis metric learning problems. In general, the proposed approach had a time complexity of O ( t times the cube of D ) with t = 20 ~ 30 for most problems in our experiments. As presented in each chapter, our experiments on various datasets in several applications showed that our algorithms can achieve comparable classification accuracy as state-of-the-art metric learning algorithms with reduced computational complexity.
9
Yeh, Yin-Cheng, and 葉胤呈. "A Thresholded Discriminative Metric Learning Approach for Deep Speaker Recognition." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/3yekj7.
Full textAbstract:
碩士國立交通大學
電子研究所
106
Speaker recognition has been widely used in many biometric security applications for decades. With the deep learning thriving today, deep models has out-performed the traditional probability-based models in many speaker recognition applications. However, compared with the studio-quality audio samples, the performance of deep models still fluctuate dramatically when background noises involved in the real-world scenario. In this thesis, we aim to build a robust speaker identification, verification, and clustering system and solve the degradation brought by background noise. To be more specific, the deep model will be refined from two perspectives, the data pre-processing and the model training stage. In the data preparation stage, noise datasets and environment filters are used to augment the data to help the model adapting the noise environment and prevent the model from over-fitting. In the model training stage, classification would be used as the initial model for further embedding training. Next, we applied our proposed embedding optimization approach, threshold center loss, to further discriminate speakers to achieve noise-resisted model on the speaker verification and clustering tasks. To sum up, this model is capable to achieve 6.48\% equal error rate and the accuracy of the speaker clustering more then 90\% if the number of speakers less than 20 in VoxCeleb Dataset.
10
Sanyal, Soubhik. "Discriminative Descriptors for Unconstrained Face and Object Recognition." Thesis, 2017. http://etd.iisc.ac.in/handle/2005/4177.
Full textAbstract:
Face and object recognition is a challenging problem in the field of computer vision. It deals with identifying faces or objects form an image or video. Due to its numerous applications in biometrics, security, multimedia processing, on-line shopping, psychology and neuroscience, automated vehicle parking systems, autonomous driving and machine inspection, it has drawn attention from a lot of researches. Researchers have studied different aspects of this problem. Among them pose robust matching is a very important problem with various applications like recognizing faces and objects in uncontrolled scenarios in which the images appear in wide variety of pose and illumination conditions along with low resolution.
In this thesis, we propose three discriminative pose-free descriptors, Subspace Point Representation (DPF-SPR), Layered Canonical Correlated (DPF-LCC ) and Aligned Discriminative Pose Robust (ADPR) descriptor, for matching faces and objects across pose. They are also robust for recognition in low resolution and varying illumination. We use training examples at very few poses to generate virtual intermediate pose subspaces. An image is represented by a feature set obtained by projecting its low-level feature on these subspaces. This way we gather more information regarding the unseen poses by generating synthetic data and make our features more robust towards unseen pose variations. Then we apply a discriminative transform to make this feature set suitable for recognition for generating two of our descriptors namely DPF-SPR and DPF-LCC. In one approach, we transform it to a vector by using subspace to point representation technique which generates our DPF-SPR descriptors. In the second approach, layered structures of canonical correlated subspaces are formed, onto which the feature set is projected which generates our DPF-LCC descriptor. In a third approach we first align the remaining subspaces with the frontal one before learning the discriminative metric and concatenate the aligned discriminative projected features to generate ADPR.
Experiments on recognizing faces and objects across varying pose are done. Specifically we have done experiments on MultiPIE and Surveillance Cameras Face database for face recognition and COIL-20 and RGB-D dataset for object recognition. We show that our approaches can even improve the recognition rate over the state-of-the-art deep learning approaches. We also perform extensive analysis of our three descriptors to get a better qualitative understanding. We compare with state-of-the-art to show the effectiveness of the proposed approaches.
Books on the topic "Metric Learning Approaches"
1
Conference, Ontario Educational Research Council. [Papers presented at the 31st Annual Conference of the Ontario Educational Research Council, Toronto, Ontario, December 8-9, 1989]. [Toronto, ON: s.n.], 1989.
Find full text
2
Conference, Ontario Educational Research Council. [Papers presented at the 30th Annual Conference of the Ontario Educational Research Council, Toronto, Ontario, December 2-3, 1988]. [Toronto, ON: s.n.], 1988.
Find full text
3
Ontario Educational Research Council. Conference. [Papers presented at the 32nd Annual Conference of the Ontario Educational Research Council, Toronto, Ontario, December 7-8, 1990]. [Ontario: s.n.], 1990.
Find full text
4
Ontario Educational Research Council. Conference. [Papers presented at the 34th Annual Conference of the Ontario Educational Research Council, Toronto, Ontario, December 4 - 5, 1992]. [Ontario: s.n.], 1992.
Find full text
5
Ontario Educational Research Council. Conference. [Papers presented at the 35th Annual Conference of the Ontario Educational Research Council, Toronto, Ontario, December 3-4, 1993]. [Toronto, Ont: s.n, 1993.
Find full text
6
Ontario Educational Research Council. Conference. [Papers presented at the 36th Annual Conference of the Ontario Educational Research Council, Toronto, Ontario, December 2-3, 1994]. [Toronto, ON: s.n.], 1994.
Find full text
7
Ontario Educational Research Council. Conference. [Papers presented at the 28th Annual Conference of the Ontario Educational Research Council, Toronto, Ontario, Dec. 1986]. [Toronto, ON: s.n.]., 1986.
Find full text
8
Ontario Educational Research Council. Conference. [Papers presented at the 33rd Annual Conference of the Ontario Educational Research Council, Toronto, Ontario, December 6-7, 1991]. [Ontario: s.n.], 1991.
Find full text
9
Winters, Bradford D., and Peter J. Pronovost. Patient safety in the ICU. Oxford University Press, 2016. http://dx.doi.org/10.1093/med/9780199600830.003.0016.
Full textAbstract:
While patient safety and quality have become a major focus of health care providers, policy makers, and customers over the last decade and a half, progress has been limited and wide quality gaps, where patient do not receive the care they should, remain. While technical improvements have gone a long way in these efforts, adaptive improvements in the culture of safety need to be more vigorously addressed. Likewise, quality metrics and a scientific approach to patient safety is necessary to ensure that interventions actually work. The Comprehensive Unit Safety Program (CUSP) strategy and its embedded Learning from Defects (LFD) process are central to creating a sustainable improvement in the culture of patient safety and quality, and in real outcomes and process improvements. CUSP is a bottom-up approach that relies on the wisdom and efforts of front-line providers who best know the safety issues in their immediate environment. The LFD process seeks to translate evidence into practice (TRiP model) building interventions and tools to improve safety and close the quality gap. The development of these interventions and tools are guided by the principles of safe design and the application of the four E’s (engagement, education, execution, and evaluation) can be successfully implemented into the health care environment with substantial improvements in safety and quality.
Book chapters on the topic "Metric Learning Approaches"
1
Fay, Damien, Hamed Haddadi, Andrew W. Moore, Richard Mortier, Andrew G. Thomason, and Steve Uhlig. "Weighted Spectral Distribution: A Metric for Structural Analysis of Networks." In Statistical and Machine Learning Approaches for Network Analysis, 153–89. Hoboken, NJ, USA: John Wiley & Sons, Inc., 2012. http://dx.doi.org/10.1002/9781118346990.ch6.
Full text
2
Vaish, Ashutosh, Sagar Gupta, and Neeru Rathee. "Enhancing Emotion Detection Using Metric Learning Approach." In Innovations in Computer Science and Engineering, 317–23. Singapore: Springer Singapore, 2018. http://dx.doi.org/10.1007/978-981-10-8201-6_36.
Full text
3
Kunapuli, Gautam, and Jude Shavlik. "Mirror Descent for Metric Learning: A Unified Approach." In Machine Learning and Knowledge Discovery in Databases, 859–74. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-33460-3_60.
Full text
4
Perez-Suay, Adrian, Francesc J. Ferri, and Jesús V. Albert. "An Online Metric Learning Approach through Margin Maximization." In Pattern Recognition and Image Analysis, 500–507. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011. http://dx.doi.org/10.1007/978-3-642-21257-4_62.
Full text
5
Liu, Meizhu, and Baba C. Vemuri. "A Robust and Efficient Doubly Regularized Metric Learning Approach." In Computer Vision – ECCV 2012, 646–59. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-33765-9_46.
Full text
6
Babagholami-Mohamadabadi, Behnam, Seyed Mahdi Roostaiyan, Ali Zarghami, and Mahdieh Soleymani Baghshah. "Multi-Modal Distance Metric Learning: ABayesian Non-parametric Approach." In Computer Vision - ECCV 2014 Workshops, 63–77. Cham: Springer International Publishing, 2015. http://dx.doi.org/10.1007/978-3-319-16199-0_5.
Full text
7
González-Vanegas, W., A. Álvarez-Meza, and A. Orozco-Gutiérrez. "An Automatic Approximate Bayesian Computation Approach Using Metric Learning." In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 12–19. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-13469-3_2.
Full text
8
Luo, Changchun, Mu Li, Hongzhi Zhang, Faqiang Wang, David Zhang, and Wangmeng Zuo. "Metric Learning with Relative Distance Constraints: A Modified SVM Approach." In Communications in Computer and Information Science, 242–49. Berlin, Heidelberg: Springer Berlin Heidelberg, 2015. http://dx.doi.org/10.1007/978-3-662-46248-5_30.
Full text
9
Caione, Adriana, Anna Lisa Guido, Roberto Paiano, Andrea Pandurino, and Stefania Pasanisi. "A Social Metric Approach to E-Learning Evaluation in Education." In Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 3–11. Cham: Springer International Publishing, 2016. http://dx.doi.org/10.1007/978-3-319-49625-2_1.
Full text
10
Suárez, Juan Luis, Germán González-Almagro, Salvador García, and Francisco Herrera. "A Preliminary Approach for using Metric Learning in Monotonic Classification." In Advances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence, 773–84. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-08530-7_65.
Full textConference papers on the topic "Metric Learning Approaches"
1
Lehinevych, Taras, and Hlybovets Andii. "Analysis of Deep Metric Learning Approaches." In 2019 IEEE International Conference on Advanced Trends in Information Theory (ATIT). IEEE, 2019. http://dx.doi.org/10.1109/atit49449.2019.9030440.
Full text
2
Wohlwend, Jeremy, Ethan R. Elenberg, Sam Altschul, Shawn Henry, and Tao Lei. "Metric Learning for Dynamic Text Classification." In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019). Stroudsburg, PA, USA: Association for Computational Linguistics, 2019. http://dx.doi.org/10.18653/v1/d19-6116.
Full text
3
Mao, Jun-Xiang, Wei Wang, and Min-Ling Zhang. "Label Specific Multi-Semantics Metric Learning for Multi-Label Classification: Global Consideration Helps." In Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California: International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/451.
Full textAbstract:
In multi-label classification, it is critical to capitalize on complicated data structures and semantic relationships. Metric learning serves as an effective strategy to provide a better measurement of distances between examples. Existing works on metric learning for multi-label classification mainly learn one single global metric that characterizes latent semantic similarity between multi-label instances. However, such single-semantics metric exploitation approaches can not capture the intrinsic properties of multi-label data possessed of rich semantics. In this paper, the first attempt towards multi-semantics metric learning for multi-label classification is investigated. Specifically, the proposed LIMIC approach simultaneously learns one global and multiple label-specific local metrics by exploiting label-specific side information. The global metric is learned to capture the commonality across all the labels and label-specific local metrics characterize the individuality of each semantic space. The combination of global metric and label-specific local metrics is utilized to construct latent semantic space for each label, in which similar intra-class instances are pushed closer and inter-class instances are pulled apart. Furthermore, metric-based label correlation regularization is constructed to maintain similarity between correlated label spaces. Extensive experiments on benchmark multi-label data sets validate the superiority of our proposed approach in learning effective distance metrics for multi-label classification.
4
Guillaumin, Matthieu, Jakob Verbeek, and Cordelia Schmid. "Is that you? Metric learning approaches for face identification." In 2009 IEEE 12th International Conference on Computer Vision (ICCV). IEEE, 2009. http://dx.doi.org/10.1109/iccv.2009.5459197.
Full text
5
Buris, Luiz H., Daniel C. G. Pedronette, Joao P. Papa, Jurandy Almeida, Gustavo Carneiro, and Fabio A. Faria. "Mixup-Based Deep Metric Learning Approaches for Incomplete Supervision." In 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022. http://dx.doi.org/10.1109/icip46576.2022.9897167.
Full text
6
Kumari, Priyadarshini, Ritesh Goru, Siddhartha Chaudhuri, and Subhasis Chaudhuri. "Batch Decorrelation for Active Metric Learning." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/312.
Full textAbstract:
We present an active learning strategy for training parametric models of distance metrics, given triplet-based similarity assessments: object $x_i$ is more similar to object $x_j$ than to $x_k$. In contrast to prior work on class-based learning, where the fundamental goal is classification and any implicit or explicit metric is binary, we focus on perceptual metrics that express the degree of (dis)similarity between objects. We find that standard active learning approaches degrade when annotations are requested for batches of triplets at a time: our studies suggest that correlation among triplets is responsible. In this work, we propose a novel method to decorrelate batches of triplets, that jointly balances informativeness and diversity while decoupling the choice of heuristic for each criterion. Experiments indicate our method is general, adaptable, and outperforms the state-of-the-art.
7
Luo, Yong, Tongliang Liu, Yonggang Wen, and Dacheng Tao. "Online Heterogeneous Transfer Metric Learning." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/350.
Full textAbstract:
Distance metric learning (DML) has been demonstrated to be successful and essential in diverse applications. Transfer metric learning (TML) can help DML in the target domain with limited label information by utilizing information from some related source domains. The heterogeneous TML (HTML), where the feature representations vary from the source to the target domain, is general and challenging. However, current HTML approaches are usually conducted in a batch manner and cannot handle sequential data. This motivates the proposed online HTML (OHTML) method. In particular, the distance metric in the source domain is pre-trained using some existing DML algorithms. To enable knowledge transfer, we assume there are large amounts of unlabeled corresponding data that have representations in both the source and target domains. By enforcing the distances (between these unlabeled samples) in the target domain to agree with those in the source domain under the manifold regularization theme, we learn an improved target metric. We formulate the problem in the online setting so that the optimization is efficient and the model can be adapted to new coming data. Experiments in diverse applications demonstrate both effectiveness and efficiency of the proposed method.
8
Chen, Pu, Xinyi Xu, and Cheng Deng. "Deep View-Aware Metric Learning for Person Re-Identification." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/86.
Full textAbstract:
Person re-identification remains a challenging issue due to the dramatic changes in visual appearance caused by the variations in camera views, human pose, and background clutter. In this paper, we propose a deep view-aware metric learning (DVAML) model, where image pairs with similar and dissimilar views are projected into different feature subspaces, which can discover the intrinsic relevance between image pairs from different aspects. Additionally, we employ multiple metrics to jointly learn feature subspaces on which the relevance between image pairs are explicitly captured and thus greatly promoting the retrieval accuracy. Extensive experiment results on datasets CUHK01, CUHK03, and PRID2011 demonstrate the superiority of our method compared with state-of-the-art approaches.
9
Pecorelli, Fabiano, Fabio Palomba, Dario Di Nucci, and Andrea De Lucia. "Comparing Heuristic and Machine Learning Approaches for Metric-Based Code Smell Detection." In 2019 IEEE/ACM 27th International Conference on Program Comprehension (ICPC). IEEE, 2019. http://dx.doi.org/10.1109/icpc.2019.00023.
Full text
10
Oregi, Izaskun, Javier Del Ser, Aritz Perez, and Jose A. Lozano. "Nature-inspired approaches for distance metric learning in multivariate time series classification." In 2017 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2017. http://dx.doi.org/10.1109/cec.2017.7969545.
Full textReports on the topic "Metric Learning Approaches"
1
Zheng, Zhonghua, Nicole Riemer, Matthew West, and Valentine G. Anantharaj. Evaluation of Machine Learning Approaches to Estimate Aerosol Mixing State Metrics in Atmospheric Models. Office of Scientific and Technical Information (OSTI), May 2019. http://dx.doi.org/10.2172/1513380.
Full text
2
Idakwo, Gabriel, Sundar Thangapandian, Joseph Luttrell, Zhaoxian Zhou, Chaoyang Zhang, and Ping Gong. Deep learning-based structure-activity relationship modeling for multi-category toxicity classification : a case study of 10K Tox21 chemicals with high-throughput cell-based androgen receptor bioassay data. Engineer Research and Development Center (U.S.), July 2021. http://dx.doi.org/10.21079/11681/41302.
Full textAbstract:
Deep learning (DL) has attracted the attention of computational toxicologists as it offers a potentially greater power for in silico predictive toxicology than existing shallow learning algorithms. However, contradicting reports have been documented. To further explore the advantages of DL over shallow learning, we conducted this case study using two cell-based androgen receptor (AR) activity datasets with 10K chemicals generated from the Tox21 program. A nested double-loop cross-validation approach was adopted along with a stratified sampling strategy for partitioning chemicals of multiple AR activity classes (i.e., agonist, antagonist, inactive, and inconclusive) at the same distribution rates amongst the training, validation and test subsets. Deep neural networks (DNN) and random forest (RF), representing deep and shallow learning algorithms, respectively, were chosen to carry out structure-activity relationship-based chemical toxicity prediction. Results suggest that DNN significantly outperformed RF (p < 0.001, ANOVA) by 22–27% for four metrics (precision, recall, F-measure, and AUPRC) and by 11% for another (AUROC). Further in-depth analyses of chemical scaffolding shed insights on structural alerts for AR agonists/antagonists and inactive/inconclusive compounds, which may aid in future drug discovery and improvement of toxicity prediction modeling.
3
Valencia, Oscar, Juan José Díaz, and Diego A. Parra. Assessing Macro-Fiscal Risk for Latin American and Caribbean Countries. Inter-American Development Bank, November 2022. http://dx.doi.org/10.18235/0004530.
Full textAbstract:
This paper provides a comprehensive early warning system (EWS) that balances the classical signaling approach with the best-realized machine learning (ML) model for predicting fiscal stress episodes. Using accumulated local effects (ALE), we compute a set of thresholds for the most informative variables that drive the correlation between predictors. In addition, to evaluate the main country risks, we propose a leading fiscal risk indicator, highlighting macro, fiscal and institutional attributes. Estimates from different models suggest significant heterogeneity among the most critical variables in determining fiscal risk across countries. While macro variables have higher relevance for advanced countries, fiscal variables were more significant for Latin American and Caribbean (LAC) and emerging economies. These results are consistent under different liquidity-solvency metrics and have deepened since the global financial crisis.
4
Hlushak, Oksana M., Svetlana O. Semenyaka, Volodymyr V. Proshkin, Stanislav V. Sapozhnykov, and Oksana S. Lytvyn. The usage of digital technologies in the university training of future bachelors (having been based on the data of mathematical subjects). [б. в.], July 2020. http://dx.doi.org/10.31812/123456789/3860.
Full textAbstract:
This article demonstrates that mathematics in the system of higher education has outgrown the status of the general education subject and should become an integral part of the professional training of future bachelors, including economists, on the basis of intersubject connection with special subjects. Such aspects as the importance of improving the scientific and methodological support of mathematical training of students by means of digital technologies are revealed. It is specified that in order to implement the task of qualified training of students learning econometrics and economic and mathematical modeling, it is necessary to use digital technologies in two directions: for the organization of electronic educational space and in the process of solving applied problems at the junction of the branches of economics and mathematics. The advantages of using e-learning courses in the educational process are presented (such as providing individualization of the educational process in accordance with the needs, characteristics and capabilities of students; improving the quality and efficiency of the educational process; ensuring systematic monitoring of the educational quality). The unified structures of “Econometrics”, “Economic and mathematical modeling” based on the Moodle platform are the following ones. The article presents the results of the pedagogical experiment on the attitude of students to the use of e-learning course (ELC) in the educational process of Borys Grinchenko Kyiv University and Alfred Nobel University (Dnipro city). We found that the following metrics need improvement: availability of time-appropriate mathematical materials; individual approach in training; students’ self-expression and the development of their creativity in the e-learning process. The following opportunities are brought to light the possibilities of digital technologies for the construction and research of econometric models (based on the problem of dependence of the level of the Ukrainian population employment). Various stages of building and testing of the econometric model are characterized: identification of variables, specification of the model, parameterization and verification of the statistical significance of the obtained results.