Relevant bibliographies by topics / Additive Angular Margin loss

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Book chapters
  4. Conference papers

Academic literature on the topic 'Additive Angular Margin loss'

Author: Grafiati
Published: 28 June 2021
Last updated: 10 February 2022

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Additive Angular Margin loss.'

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 "Additive Angular Margin loss"

1

Zhou, Shengwei, Caikou Chen, Guojiang Han, and Xielian Hou. "Double Additive Margin Softmax Loss for Face Recognition." Applied Sciences 10, no. 1 (December 19, 2019): 60. http://dx.doi.org/10.3390/app10010060.

Full text
Abstract:
Learning large-margin face features whose intra-class variance is small and inter-class diversity is one of important challenges in feature learning applying Deep Convolutional Neural Networks (DCNNs) for face recognition. Recently, an appealing line of research is to incorporate an angular margin in the original softmax loss functions for obtaining discriminative deep features during the training of DCNNs. In this paper we propose a novel loss function, termed as double additive margin Softmax loss (DAM-Softmax). The presented loss has a clearer geometrical explanation and can obtain highly discriminative features for face recognition. Extensive experimental evaluation of several recent state-of-the-art softmax loss functions are conducted on the relevant face recognition benchmarks, CASIA-Webface, LFW, CALFW, CPLFW, and CFP-FP. We show that the proposed loss function consistently outperforms the state-of-the-art.
APA, Harvard, Vancouver, ISO, and other styles
2

Wang, Xiaobo, Shifeng Zhang, Shuo Wang, Tianyu Fu, Hailin Shi, and Tao Mei. "Mis-Classified Vector Guided Softmax Loss for Face Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 12241–48. http://dx.doi.org/10.1609/aaai.v34i07.6906.

Full text
Abstract:
Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (e.g., angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from three issues: 1) Obviously, they ignore the importance of informative features mining for discriminative learning; 2) They encourage the feature margin only from the ground truth class, without realizing the discriminability from other non-ground truth classes; 3) The feature margin between different classes is set to be same and fixed, which may not adapt the situations very well. To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative face features. To the best of our knowledge, this is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function. Experimental results on several benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives. Our code is available at http://www.cbsr.ia.ac.cn/users/xiaobowang/.
APA, Harvard, Vancouver, ISO, and other styles
3

Kajla, Nadeem Iqbal, Malik Muhammad Saad Missen, Muhammad Muzzamil Luqman, Mickael Coustaty, Arif Mehmood, and Gyu Sang Choi. "Additive Angular Margin Loss in Deep Graph Neural Network Classifier for Learning Graph Edit Distance." IEEE Access 8 (2020): 201752–61. http://dx.doi.org/10.1109/access.2020.3035886.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Liu, Wenting, Li Zhou, and Jie Chen. "Face Recognition Based on Lightweight Convolutional Neural Networks." Information 12, no. 5 (April 28, 2021): 191. http://dx.doi.org/10.3390/info12050191.

Full text
Abstract:
Face recognition algorithms based on deep learning methods have become increasingly popular. Most of these are based on highly precise but complex convolutional neural networks (CNNs), which require significant computing resources and storage, and are difficult to deploy on mobile devices or embedded terminals. In this paper, we propose several methods to improve the algorithms for face recognition based on a lightweight CNN, which is further optimized in terms of the network architecture and training pattern on the basis of MobileFaceNet. Regarding the network architecture, we introduce the Squeeze-and-Excitation (SE) block and propose three improved structures via a channel attention mechanism—the depthwise SE module, the depthwise separable SE module, and the linear SE module—which are able to learn the correlation of information between channels and assign them different weights. In addition, a novel training method for the face recognition task combined with an additive angular margin loss function is proposed that performs the compression and knowledge transfer of the deep network for face recognition. Finally, we obtained high-precision and lightweight face recognition models with fewer parameters and calculations that are more suitable for applications. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed methods.
APA, Harvard, Vancouver, ISO, and other styles
5

Sun, Jingna, Wenming Yang, Riqiang Gao, Jing-Hao Xue, and Qingmin Liao. "Inter-class angular margin loss for face recognition." Signal Processing: Image Communication 80 (February 2020): 115636. http://dx.doi.org/10.1016/j.image.2019.115636.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Kim, Taehyeon, Eungi Hong, and Yoonsik Choe. "Deep Morphological Anomaly Detection Based on Angular Margin Loss." Applied Sciences 11, no. 14 (July 16, 2021): 6545. http://dx.doi.org/10.3390/app11146545.

Full text
Abstract:
Deep anomaly detection aims to identify “abnormal” data by utilizing a deep neural network trained on a normal training dataset. In general, industrial visual anomaly detection systems distinguish between normal and “abnormal” data through small morphological differences such as cracks and stains. Nevertheless, most existing algorithms emphasize capturing the semantic features of normal data rather than the morphological features. Therefore, they yield poor performance on real-world visual inspection, although they show their superiority in simulations with representative image classification datasets. To address this limitation, we propose a novel deep anomaly detection algorithm based on the salient morphological features of normal data. The main idea behind the proposed algorithm is to train a multiclass model to classify hundreds of morphological transformation cases applied to all the given data. To this end, the proposed algorithm utilizes a self-supervised learning strategy, making unsupervised learning straightforward. Additionally, to enhance the performance of the proposed algorithm, we replaced the cross-entropy-based loss function with the angular margin loss function. It is experimentally demonstrated that the proposed algorithm outperforms several recent anomaly detection methodologies in various datasets.
APA, Harvard, Vancouver, ISO, and other styles
7

Li, Zhaoqun, Cheng Xu, and Biao Leng. "Angular Triplet-Center Loss for Multi-View 3D Shape Retrieval." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 8682–89. http://dx.doi.org/10.1609/aaai.v33i01.33018682.

Full text
Abstract:
How to obtain the desirable representation of a 3D shape, which is discriminative across categories and polymerized within classes, is a significant challenge in 3D shape retrieval. Most existing 3D shape retrieval methods focus on capturing strong discriminative shape representation with softmax loss for the classification task, while the shape feature learning with metric loss is neglected for 3D shape retrieval. In this paper, we address this problem based on the intuition that the cosine distance of shape embeddings should be close enough within the same class and far away across categories. Since most of 3D shape retrieval tasks use cosine distance of shape features for measuring shape similarity, we propose a novel metric loss named angular triplet-center loss, which directly optimizes the cosine distances between the features. It inherits the triplet-center loss property to achieve larger inter-class distance and smaller intra-class distance simultaneously. Unlike previous metric loss utilized in 3D shape retrieval methods, where Euclidean distance is adopted and the margin design is difficult, the proposed method is more convenient to train feature embeddings and more suitable for 3D shape retrieval. Moreover, the angle margin is adopted to replace the cosine margin in order to provide more explicit discriminative constraints on an embedding space. Extensive experimental results on two popular 3D object retrieval benchmarks, ModelNet40 and ShapeNetCore 55, demonstrate the effectiveness of our proposed loss, and our method has achieved state-ofthe-art results on various 3D shape datasets.
APA, Harvard, Vancouver, ISO, and other styles
8

Chowdhury, Labib, Hasib Zunair, and Nabeel Mohammed. "Robust Deep Speaker Recognition: Learning Latent Representation with Joint Angular Margin Loss." Applied Sciences 10, no. 21 (October 26, 2020): 7522. http://dx.doi.org/10.3390/app10217522.

Full text
Abstract:
Speaker identification is gaining popularity, with notable applications in security, automation, and authentication. For speaker identification, deep-convolutional-network-based approaches, such as SincNet, are used as an alternative to i-vectors. Convolution performed by parameterized sinc functions in SincNet demonstrated superior results in this area. This system optimizes softmax loss, which is integrated in the classification layer that is responsible for making predictions. Since the nature of this loss is only to increase interclass distance, it is not always an optimal design choice for biometric-authentication tasks such as face and speaker recognition. To overcome the aforementioned issues, this study proposes a family of models that improve upon the state-of-the-art SincNet model. Proposed models AF-SincNet, Ensemble-SincNet, and ALL-SincNet serve as a potential successor to the successful SincNet model. The proposed models are compared on a number of speaker-recognition datasets, such as TIMIT and LibriSpeech, with their own unique challenges. Performance improvements are demonstrated compared to competitive baselines. In interdataset evaluation, the best reported model not only consistently outperformed the baselines and current prior models, but also generalized well on unseen and diverse tasks such as Bengali speaker recognition.
APA, Harvard, Vancouver, ISO, and other styles
9

Девисилов, Vladimir Devisilov, Шарай, and E. Sharay. "Current Stability Limits in Hydrodynamic Filter." Safety in Technosphere 2, no. 4 (August 25, 2013): 23–29. http://dx.doi.org/10.12737/717.

Full text
Abstract:
The phenomenon related to a loss of laminar stability of fluid flow in hydrodynamic filter’s working zone with formation of toroidal vortexes is considered. Estimated results related to numerical modeling of liquid’s stationary current in a gap between two coaxial cylinders are presented under various boundary conditions. It is shown that existence of liquid suction from rotating internal cylinder surface leads to stabilization and increase of flow’s stability margin in hydrodynamic filters. The flow stability limits depending on Taylor´s number, rotating cylinder’s angular velocity and liquid suction speed through the cylinder’s surface are defined.
APA, Harvard, Vancouver, ISO, and other styles
10

Allen, B., T. Pelham, Y. Wu, T. Drysdale, D. Isakov, C. Gamlath, C. J. Stevens, G. Hilton, M. A. Beach, and P. S. Grant. "Experimental evaluation of 3D printed spiral phase plates for enabling an orbital angular momentum multiplexed radio system." Royal Society Open Science 6, no. 12 (December 2019): 191419. http://dx.doi.org/10.1098/rsos.191419.

Full text
Abstract:
This paper evaluates the performance of three-dimensionally (3D) printed spiral phase plates (SPPs) for enabling an orbital angular momentum (OAM) multiplexed radio system. The design and realization of the SPPs by means of additive manufacturing exploiting a high-permittivity material is described. Modes 1 and 2 SPPs are then evaluated at 15 GHz in terms of 3D complex radiation pattern, mode purity and beam collimation by means of a 3D printed dielectric lens. The results with the lens yield a crosstalk of −8 dB for between modes 1 and −1, and −11.4 dB for between modes 2 and −2. We suggest a mode multiplexer architecture that is expected to further reduce the crosstalk for each mode. An additional loss of 4.2 dB is incurred with the SPPs inserted into the communication link, which is undesirable for obtaining reliable LTE-based communications. Thus, we suggest: using lower loss materials, seeking ways to reduce material interface reflections or alternative ways of OAM multiplexing to realize a viable OAM multiplexed radio system.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "Additive Angular Margin loss"

1

Lukáč, Peter. "Verifikace osob podle hlasu bez extrakce příznaků." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2021. http://www.nusl.cz/ntk/nusl-445531.

Full text
Abstract:
Verifikácia osôb je oblasť, ktorá sa stále modernizuje, zlepšuje a snaží sa vyhovieť požiadavkám, ktoré sa na ňu kladú vo oblastiach využitia ako sú autorizačné systmémy, forenzné analýzy, atď. Vylepšenia sa uskutočňujú vďaka pokrom v hlbokom učení, tvorením nových trénovacích a testovacích dátovych sad a rôznych súťaží vo verifikácií osôb a workshopov. V tejto práci preskúmame modely pre verifikáciu osôb bez extrakcie príznakov. Používanie nespracovaných zvukových stôp ako vstupy modelov zjednodušuje spracovávanie vstpu a teda znižujú sa výpočetné a pamäťové požiadavky a redukuje sa počet hyperparametrov potrebných pre tvorbu príznakov z nahrávok, ktoré ovplivňujú výsledky. Momentálne modely bez extrakcie príznakov nedosahujú výsledky modelov s extrakciou príznakov. Na základných modeloch budeme experimentovať s modernými technikamy a budeme sa snažiť zlepšiť presnosť modelov. Experimenty s modernými technikamy značne zlepšili výsledky základných modelov ale stále sme nedosiahli výsledky vylepšeného modelu s extrakciou príznakov. Zlepšenie je ale dostatočné nato aby sme vytovrili fúziu so s týmto modelom. Záverom diskutujeme dosiahnuté výsledky a navrhujeme zlepšenia na základe týchto výsledkov.
APA, Harvard, Vancouver, ISO, and other styles
2

Ul, Rahman Jamshaid. "A Study on Angular Softmax." Doctoral thesis, 2020. http://hdl.handle.net/10316/95693.

Full text
Abstract:
Documentos apresentados no âmbito do reconhecimento de graus e diplomas estrangeiros
After the development of Deepface and DeepID methods in 2014, deep learning methods for image recognition has dramatically improved the state-of-the-art performance on Deep Convolutional Neural Networks (DCNNs) and reshaped the research landscape of image processing and data analysis. In spite of rapid improvement in deep learning algorithms, it still has various challenges like adjustment of appropriate loss function and optimization strategy to handle large scale problems in many computer vision applications including Face Recognition (FR) and Handwritten Digit Recognition (HDR). This thesis focus on these challenges and their better solution.
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "Additive Angular Margin loss"

1

Zhou, Shengyao, Junfan Luo, Junkun Zhou, and Xiang Ji. "AsArcFace: Asymmetric Additive Angular Margin Loss for Fairface Recognition." In Computer Vision – ECCV 2020 Workshops, 482–91. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-65414-6_33.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Suzuki, Rikiya, Sumio Fujita, and Tetsuya Sakai. "Arc Loss: Softmax with Additive Angular Margin for Answer Retrieval." In Information Retrieval Technology, 34–40. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-42835-8_4.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Liu, Weilun, Jichao Jiao, Yaokai Mo, Jian Jiao, and Zhongliang Deng. "MaaFace: Multiplicative and Additive Angular Margin Loss for Deep Face Recognition." In Lecture Notes in Computer Science, 642–53. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-34113-8_53.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Ali, Sharib, Binod Bhattarai, Tae-Kyun Kim, and Jens Rittscher. "Additive Angular Margin for Few Shot Learning to Classify Clinical Endoscopy Images." In Machine Learning in Medical Imaging, 494–503. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-59861-7_50.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Iqbal, Mansoor, Muhammad Awais Rehman, Naveed Iqbal, and Zaheer Iqbal. "Effect of Laplacian Smoothing Stochastic Gradient Descent with Angular Margin Softmax Loss on Face Recognition." In Communications in Computer and Information Science, 549–61. Singapore: Springer Singapore, 2020. http://dx.doi.org/10.1007/978-981-15-5232-8_47.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Additive Angular Margin loss"

1

Zhao, He, Yongjie Shi, Xin Tong, Xianghua Ying, and Hongbin Zha. "Qamface: Quadratic Additive Angular Margin Loss For Face Recognition." In 2020 IEEE International Conference on Image Processing (ICIP). IEEE, 2020. http://dx.doi.org/10.1109/icip40778.2020.9191004.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Deng, Jiankang, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. "ArcFace: Additive Angular Margin Loss for Deep Face Recognition." In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2019. http://dx.doi.org/10.1109/cvpr.2019.00482.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

SU, Jie, Xiaohai He, Linbo Qing, Yanmei Yu, Shengyu Xu, and Yonghong Peng. "A New Discriminative Feature Learning for Person Re-Identification Using Additive Angular Margin Softmax Loss." In 2019 UK/ China Emerging Technologies (UCET). IEEE, 2019. http://dx.doi.org/10.1109/ucet.2019.8881838.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Cao, Bing, Nannan Wang, Xinbo Gao, Jie Li, and Zhifeng Li. "Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/96.

Full text
Abstract:
Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios. However, HFR is still a challenging problem due to the significant cross-domain discrepancy and the lacking of sufficient training data in different domains. This paper presents a deep neural network approach namely Multi-Margin based Decorrelation Learning (MMDL) to extract decorrelation representations in a hyperspherical space for cross-domain face images. The proposed framework can be divided into two components: heterogeneous representation network and decorrelation representation learning. First, we employ a large scale of accessible visual face images to train heterogeneous representation network. The decorrelation layer projects the output of the first component into decorrelation latent subspace and obtain decorrelation representation. In addition, we design a multi-margin loss (MML), which consists of tetradmargin loss (TML) and heterogeneous angular margin loss (HAML), to constrain the proposed framework. Experimental results on two challenging heterogeneous face databases show that our approach achieves superior performance on both verification and recognition tasks, comparing with state-of-the-art methods.
APA, Harvard, Vancouver, ISO, and other styles
5

Wu, Jiantao, and Lin Wang. "ArcGrad: Angular Gradient Margin Loss for Classification." In 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020. http://dx.doi.org/10.1109/ijcnn48605.2020.9207251.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Rouhani, Bahman, Ali Samadzadeh, Mohammad Rahmati, and Ahmad Nickabadi. "Gaussian Soft Margin Angular Loss for Face Recognition." In 2020 International Conference on Machine Vision and Image Processing (MVIP). IEEE, 2020. http://dx.doi.org/10.1109/mvip49855.2020.9116917.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Li, Qiang, Xianzhen He, Wenguang Wang, and Shiming Ge. "AeMFace: Additive E-Margin Loss for Deep Face Recognition." In 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP). IEEE, 2019. http://dx.doi.org/10.1109/icsidp47821.2019.9173230.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Jiang, Mingchao, Zhenguo Yang, Wenyin Liu, and Xiaochun Liu. "Additive Margin Softmax with Center Loss for Face Recognition." In ICVIP 2018: 2018 the 2nd International Conference on Video and Image Processing. New York, NY, USA: ACM, 2018. http://dx.doi.org/10.1145/3301506.3301511.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Li, Zheng, Yan Liu, Lin Li, and Qingyang Hong. "Additive Phoneme-Aware Margin Softmax Loss for Language Recognition." In Interspeech 2021. ISCA: ISCA, 2021. http://dx.doi.org/10.21437/interspeech.2021-1167.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Wei, Yuheng, Junzhao Du, and Hui Liu. "Angular Margin Centroid Loss for Text-Independent Speaker Recognition." In Interspeech 2020. ISCA: ISCA, 2020. http://dx.doi.org/10.21437/interspeech.2020-2538.

Full text
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Additive Angular Margin loss' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography