Bibliografias temáticas / Convolution dilatée

Índice

Artigos de revistas
Teses / dissertações
Capítulos de livros
Trabalhos de conferências

Literatura científica selecionada sobre o tema "Convolution dilatée"

Autor: Grafiati

Publicado: 24 de agosto de 2024

Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos

Selecione um tipo de fonte:

Consulte a lista de atuais artigos, livros, teses, anais de congressos e outras fontes científicas relevantes para o tema "Convolution dilatée".

Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.

Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.

Artigos de revistas sobre o assunto "Convolution dilatée"

Wang, Wei, Yiyang Hu, Ting Zou, Hongmei Liu, Jin Wang e Xin Wang. "A New Image Classification Approach via Improved MobileNet Models with Local Receptive Field Expansion in Shallow Layers". Computational Intelligence and Neuroscience 2020 (1 de agosto de 2020): 1–10. http://dx.doi.org/10.1155/2020/8817849.

Texto completo da fonte

Resumo:

Because deep neural networks (DNNs) are both memory-intensive and computation-intensive, they are difficult to apply to embedded systems with limited hardware resources. Therefore, DNN models need to be compressed and accelerated. By applying depthwise separable convolutions, MobileNet can decrease the number of parameters and computational complexity with less loss of classification precision. Based on MobileNet, 3 improved MobileNet models with local receptive field expansion in shallow layers, also called Dilated-MobileNet (Dilated Convolution MobileNet) models, are proposed, in which dilated convolutions are introduced into a specific convolutional layer of the MobileNet model. Without increasing the number of parameters, dilated convolutions are used to increase the receptive field of the convolution filters to obtain better classification accuracy. The experiments were performed on the Caltech-101, Caltech-256, and Tubingen animals with attribute datasets, respectively. The results show that Dilated-MobileNets can obtain up to 2% higher classification accuracy than MobileNet.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Peng, Wenli, Shenglai Zhen, Xin Chen, Qianjing Xiong e Benli Yu. "Study on convolutional recurrent neural networks for speech enhancement in fiber-optic microphones". Journal of Physics: Conference Series 2246, n.º 1 (1 de abril de 2022): 012084. http://dx.doi.org/10.1088/1742-6596/2246/1/012084.

Texto completo da fonte

Resumo:

Abstract In this paper, several improved convolutional recurrent networks (CRN) are proposed, which can enhance the speech with non-additive distortion captured by fiber-optic microphones. Our preliminary study shows that the original CRN structure based on amplitude spectrum estimation is seriously distorted due to the loss of phase information. Therefore, we transform the network to run in time domain and gain 0.42 improvement on PESQ and 0.03 improvement on STOI. In addition, we integrate dilated convolution into CRN architecture, and adopt three different types of bottleneck modules, namely long short-term memory (LSTM), gated recurrent units (GRU) and dilated convolutions. The experimental results show that the model with dilated convolution in the encoder-decoder and the model with dilated convolution at bottleneck layer have the highest PESQ and STOI scores, respectively.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Chim, Seyha, Jin-Gu Lee e Ho-Hyun Park. "Dilated Skip Convolution for Facial Landmark Detection". Sensors 19, n.º 24 (4 de dezembro de 2019): 5350. http://dx.doi.org/10.3390/s19245350.

Texto completo da fonte

Resumo:

Facial landmark detection has gained enormous interest for face-related applications due to its success in facial analysis tasks such as facial recognition, cartoon generation, face tracking and facial expression analysis. Many studies have been proposed and implemented to deal with the challenging problems of localizing facial landmarks from given images, including large appearance variations and partial occlusion. Studies have differed in the way they use the facial appearances and shape information of input images. In our work, we consider facial information within both global and local contexts. We aim to obtain local pixel-level accuracy for local-context information in the first stage and integrate this with knowledge of spatial relationships between each key point in a whole image for global-context information in the second stage. Thus, the pipeline of our architecture consists of two main components: (1) a deep network for local-context subnet that generates detection heatmaps via fully convolutional DenseNets with additional kernel convolution filters and (2) a dilated skip convolution subnet—a combination of dilated convolutions and skip-connections networks—that are in charge of robustly refining the local appearance heatmaps. Through this proposed architecture, we demonstrate that our approach achieves state-of-the-art performance on challenging datasets—including LFPW, HELEN, 300W and AFLW2000-3D—by leveraging fully convolutional DenseNets, skip-connections and dilated convolution architecture without further post-processing.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Zhao, Feng, Junjie Zhang, Zhe Meng e Hanqiang Liu. "Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification". Remote Sensing 13, n.º 17 (26 de agosto de 2021): 3396. http://dx.doi.org/10.3390/rs13173396.

Texto completo da fonte

Resumo:

Recently, with the extensive application of deep learning techniques in the hyperspectral image (HSI) field, particularly convolutional neural network (CNN), the research of HSI classification has stepped into a new stage. To avoid the problem that the receptive field of naive convolution is small, the dilated convolution is introduced into the field of HSI classification. However, the dilated convolution usually generates blind spots in the receptive field, resulting in discontinuous spatial information obtained. In order to solve the above problem, a densely connected pyramidal dilated convolutional network (PDCNet) is proposed in this paper. Firstly, a pyramidal dilated convolutional (PDC) layer integrates different numbers of sub-dilated convolutional layers is proposed, where the dilated factor of the sub-dilated convolution increases exponentially, achieving multi-sacle receptive fields. Secondly, the number of sub-dilated convolutional layers increases in a pyramidal pattern with the depth of the network, thereby capturing more comprehensive hyperspectral information in the receptive field. Furthermore, a feature fusion mechanism combining pixel-by-pixel addition and channel stacking is adopted to extract more abstract spectral–spatial features. Finally, in order to reuse the features of the previous layers more effectively, dense connections are applied in densely pyramidal dilated convolutional (DPDC) blocks. Experiments on three well-known HSI datasets indicate that PDCNet proposed in this paper has good classification performance compared with other popular models.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Tang, Jingfan, Meijia Zhou, Pengfei Li, Min Zhang e Ming Jiang. "Crowd Counting Based on Multiresolution Density Map and Parallel Dilated Convolution". Scientific Programming 2021 (20 de janeiro de 2021): 1–10. http://dx.doi.org/10.1155/2021/8831458.

Texto completo da fonte

Resumo:

The current crowd counting tasks rely on a fully convolutional network to generate a density map that can achieve good performance. However, due to the crowd occlusion and perspective distortion in the image, the directly generated density map usually neglects the scale information and spatial contact information. To solve it, we proposed MDPDNet (Multiresolution Density maps and Parallel Dilated convolutions’ Network) to reduce the influence of occlusion and distortion on crowd estimation. This network is composed of two modules: (1) the parallel dilated convolution module (PDM) that combines three dilated convolutions in parallel to obtain the deep features on the larger receptive field with fewer parameters while reducing the loss of multiscale information; (2) the multiresolution density map module (MDM) that contains three-branch networks for extracting spatial contact information on three different low-resolution density maps as the feature input of the final crowd density map. Experiments show that MDPDNet achieved excellent results on three mainstream datasets (ShanghaiTech, UCF_CC_50, and UCF-QNRF).

Estilos ABNT, Harvard, Vancouver, APA, etc.

Ma, Tian, Xinlei Zhou, Jiayi Yang, Boyang Meng, Jiali Qian, Jiehui Zhang e Gang Ge. "Dental Lesion Segmentation Using an Improved ICNet Network with Attention". Micromachines 13, n.º 11 (7 de novembro de 2022): 1920. http://dx.doi.org/10.3390/mi13111920.

Texto completo da fonte

Resumo:

Precise segmentation of tooth lesions is critical to creation of an intelligent tooth lesion detection system. As a solution to the problem that tooth lesions are similar to normal tooth tissues and difficult to segment, an improved segmentation method of the image cascade network (ICNet) network is proposed to segment various lesion types, such as calculus, gingivitis, and tartar. First, the ICNet network model is used to achieve real-time segmentation of lesions. Second, the Convolutional Block Attention Module (CBAM) is integrated into the ICNet network structure, and large-size convolutions in the spatial attention module are replaced with layered dilated convolutions to enhance the relevant features while suppressing useless features and solve the problem of inaccurate lesion segmentations. Finally, part of the convolution in the network model is replaced with an asymmetric convolution to reduce the calculations added by the attention module. Experimental results show that compared with Fully Convolutional Networks (FCN), U-Net, SegNet, and other segmentation algorithms, our method has a significant improvement in the segmentation effect, and the image processing frequency is higher, which satisfies the real-time requirements of tooth lesion segmentation accuracy.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Song, Zhendong, Yupeng Ma, Fang Tan e Xiaoyi Feng. "Hybrid Dilated and Recursive Recurrent Convolution Network for Time-Domain Speech Enhancement". Applied Sciences 12, n.º 7 (29 de março de 2022): 3461. http://dx.doi.org/10.3390/app12073461.

Texto completo da fonte

Resumo:

In this paper, we propose a fully convolutional neural network based on recursive recurrent convolution for monaural speech enhancement in the time domain. The proposed network is an encoder-decoder structure using a series of hybrid dilated modules (HDM). The encoder creates low-dimensional features of a noisy input frame. In the HDM, the dilated convolution is used to expand the receptive field of the network model. In contrast, the standard convolution is used to make up for the under-utilized local information of the dilated convolution. The decoder is used to reconstruct enhanced frames. The recursive recurrent convolutional network uses GRU to solve the problem of multiple training parameters and complex structures. State-of-the-art results are achieved on two commonly used speech datasets.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Viriyasaranon, Thanaporn, Seung-Hoon Chae e Jang-Hwan Choi. "MFA-net: Object detection for complex X-ray cargo and baggage security imagery". PLOS ONE 17, n.º 9 (1 de setembro de 2022): e0272961. http://dx.doi.org/10.1371/journal.pone.0272961.

Texto completo da fonte

Resumo:

Deep convolutional networks have been developed to detect prohibited items for automated inspection of X-ray screening systems in the transport security system. To our knowledge, the existing frameworks were developed to recognize threats using only baggage security X-ray scans. Therefore, the detection accuracy in other domains of security X-ray scans, such as cargo X-ray scans, cannot be ensured. We propose an object detection method for efficiently detecting contraband items in both cargo and baggage for X-ray security scans. The proposed network, MFA-net, consists of three plug-and-play modules, including the multiscale dilated convolutional module, fusion feature pyramid network, and auxiliary point detection head. First, the multiscale dilated convolutional module converts the standard convolution of the detector backbone to a conditional convolution by aggregating the features from multiple dilated convolutions using dynamic feature selection to overcome the object-scale variant issue. Second, the fusion feature pyramid network combines the proposed attention and fusion modules to enhance multiscale object recognition and alleviate the object and occlusion problem. Third, the auxiliary point detection head adopts an auxiliary head to predict the new keypoints of the bounding box to emphasize the localizability without requiring further ground-truth information. We tested the performance of the MFA-net on two large-scale X-ray security image datasets from different domains: a Security Inspection X-ray (SIXray) dataset in the baggage domain and our dataset, named CargoX, in the cargo domain. Moreover, MFA-net outperformed state-of-the-art object detectors in both domains. Thus, adopting the proposed modules can further increase the detection capability of the current object detectors on X-ray security images.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Zhang, Jianming, Chaoquan Lu, Jin Wang, Lei Wang e Xiao-Guang Yue. "Concrete Cracks Detection Based on FCN with Dilated Convolution". Applied Sciences 9, n.º 13 (1 de julho de 2019): 2686. http://dx.doi.org/10.3390/app9132686.

Texto completo da fonte

Resumo:

In civil engineering, the stability of concrete is of great significance to safety of people’s life and property, so it is necessary to detect concrete damage effectively. In this paper, we treat crack detection on concrete surface as a semantic segmentation task that distinguishes background from crack at the pixel level. Inspired by Fully Convolutional Networks (FCN), we propose a full convolution network based on dilated convolution for concrete crack detection, which consists of an encoder and a decoder. Specifically, we first used the residual network to extract the feature maps of the input image, designed the dilated convolutions with different dilation rates to extract the feature maps of different receptive fields, and fused the extracted features from multiple branches. Then, we exploited the stacked deconvolution to do up-sampling operator in the fused feature maps. Finally, we used the SoftMax function to classify the feature maps at the pixel level. In order to verify the validity of the model, we introduced the commonly used evaluation indicators of semantic segmentation: Pixel Accuracy (PA), Mean Pixel Accuracy (MPA), Mean Intersection over Union (MIoU), and Frequency Weighted Intersection over Union (FWIoU). The experimental results show that the proposed model converges faster and has better generalization performance on the test set by introducing dilated convolutions with different dilation rates and a multi-branch fusion strategy. Our model has a PA of 96.84%, MPA of 92.55%, MIoU of 86.05% and FWIoU of 94.22% on the test set, which is superior to other models.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Rahman, Takowa, Md Saiful Islam e Jia Uddin. "MRI-Based Brain Tumor Classification Using a Dilated Parallel Deep Convolutional Neural Network". Digital 4, n.º 3 (28 de junho de 2024): 529–54. http://dx.doi.org/10.3390/digital4030027.

Texto completo da fonte

Resumo:

Brain tumors are frequently classified with high accuracy using convolutional neural networks (CNNs) to better comprehend the spatial connections among pixels in complex pictures. Due to their tiny receptive fields, the majority of deep convolutional neural network (DCNN)-based techniques overfit and are unable to extract global context information from more significant regions. While dilated convolution retains data resolution at the output layer and increases the receptive field without adding computation, stacking several dilated convolutions has the drawback of producing a grid effect. This research suggests a dilated parallel deep convolutional neural network (PDCNN) architecture that preserves a wide receptive field in order to handle gridding artifacts and extract both coarse and fine features from the images. This article applies multiple preprocessing strategies to the input MRI images used to train the model. By contrasting various dilation rates, the global path uses a low dilation rate (2,1,1), while the local path uses a high dilation rate (4,2,1) for decremental even numbers to tackle gridding artifacts and to extract both coarse and fine features from the two parallel paths. Using three different types of MRI datasets, the suggested dilated PDCNN with the average ensemble method performs best. The accuracy achieved for the multiclass Kaggle dataset-III, Figshare dataset-II, and binary tumor identification dataset-I is 98.35%, 98.13%, and 98.67%, respectively. In comparison to state-of-the-art techniques, the suggested structure improves results by extracting both fine and coarse features, making it efficient.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Mais fontes

Teses / dissertações sobre o assunto "Convolution dilatée"

Khalfaoui, Hassani Ismail. "Convolution dilatée avec espacements apprenables". Electronic Thesis or Diss., Université de Toulouse (2023-....), 2024. http://www.theses.fr/2024TLSES017.

Texto completo da fonte

Resumo:

Dans cette thèse, nous avons développé et étudié la méthode de convolution dilatée avec espacements apprenables (Dilated Convolution with Learnable Spacings en anglais, qu'on abrégera par le sigle DCLS). La méthode DCLS peut être considérée comme une extension de la méthode de convolution dilatée standard, mais dans laquelle les positions des poids d'un réseau de neurones sont apprises grâce à l'algorithme de rétropropagation du gradient, et ce, à l'aide d'une technique d'interpolation. Par suite, nous avons démontré empiriquement l'efficacité de la méthode DCLS en fournissant des preuves concrètes, issues de nombreuses expériences en apprentissage supervisé. Ces expériences sont issues des domaines de la vision par ordinateur, de l'audio et du traitement de la parole et toutes montrent que la méthode DCLS a un avantage compétitif sur les techniques standards de convolution ainsi que sur plusieurs méthodes de convolution avancées. Notre approche s'est faite en plusieurs étapes, en commençant par une analyse de la littérature et des techniques de convolution existantes qui ont précédé le développement de la méthode DCLS. Nous nous sommes particulièrement intéressés aux méthodes étroitement liées à la nôtre et qui demeurent essentielles pour saisir les nuances ainsi que le caractère unique de notre approche. La pierre angulaire de notre étude repose sur l'introduction et l'application de la méthode DCLS aux réseaux neuronaux convolutifs (CNN), mais aussi aux architectures hybrides qui se basent à la fois sur des méthodes convolutives et des méthodes d'attention visuelle. La méthode DCLS est particulièrement remarquable pour ses capacités dans les tâches supervisées de vision par ordinateur telles que la classification, la segmentation et la détection d'objets, qui sont toutes des tâches essentielles dans ce domaine. Ayant développé la méthode DCLS à l'origine avec une interpolation bilinéaire, nous avons entrepris l'exploration d'autres méthodes d'interpolation susceptibles de remplacer l'interpolation bilinéaire, traditionnellement utilisée dans DCLS, ainsi que d'autres méthodes de convolution, et qui visent à rendre différentiables les paramètres de positions des poids dans le noyau de convolution. L'interpolation gaussienne s'est avérée être légèrement meilleure en termes de performances. Notre recherche nous a amené par la suite à appliquer la méthode DCLS dans le domaine des réseaux de neurones à spikes (SNN) afin de permettre l'apprentissage des délais synaptiques à l'intérieur d'un réseau de neurones qui pourrait être éventuellement transféré à des puces dites neuromorphiques. Les résultats montrent que la méthode DCLS se tient comme nouvel état de l'art des SNNs en classification audio pour certaines tâches de référence dans ce domaine. Ces dernières tâches portent sur des ensembles de données connus pour avoir une composante temporelle importante. En outre, nous montrons aussi que DCLS permet d'améliorer de manière significative la précision des réseaux neuronaux artificiels pour la tâche de classification audio multi-label, un aboutissement clé dans l'un des benchmarks de classification audio les plus importants. Enfin, nous concluons par une discussion sur le dispositif expérimental choisi, ses limites, les limites de notre méthode et nos résultats
In this thesis, we develop and study the Dilated Convolution with Learnable Spacings (DCLS) method. The DCLS method can be considered as an extension of the standard dilated convolution method, but in which the positions of the weights of a neural network are learned during training by the gradient backpropagation algorithm, thanks to an interpolation technique. We empirically demonstrate the effectiveness of the DCLS method by providing concrete evidence from numerous supervised learning experiments. These experiments are drawn from the fields of computer vision, audio, and speech processing, and all show that the DCLS method has a competitive advantage over standard convolution techniques, as well as over several advanced convolution methods. Our approach is structured in several steps, starting with an analysis of the literature and existing convolution techniques that preceded the development of the DCLS method. We were particularly interested in the methods that are closely related to our own and that remain essential to capture the nuances and uniqueness of our approach. The cornerstone of our study is the introduction and application of the DCLS method to convolutional neural networks (CNNs), as well as to hybrid architectures that rely on both convolutional and visual attention approaches. The DCLS method is particularly noteworthy for its capabilities in supervised computer vision tasks such as classification, semantic segmentation, and object detection, all of which are essential tasks in the field. Having originally developed the DCLS method with bilinear interpolation, we explored other interpolation methods that could replace the bilinear interpolation conventionally used in DCLS, and which aim to make the position parameters of the weights in the convolution kernel differentiable. Gaussian interpolation proved to be slightly better in terms of performance. Our research then led us to apply the DCLS method in the field of spiking neural networks (SNNs) to enable synaptic delay learning within a neural network that could eventually be transferred to so-called neuromorphic chips. The results show that the DCLS method stands out as a new state-of-the-art technique in SNN audio classification for certain benchmark tasks in this field. These tasks involve datasets with a high temporal component. In addition, we show that DCLS can significantly improve the accuracy of artificial neural networks for the multi-label audio classification task, a key achievement in one of the most important audio classification benchmarks. We conclude with a discussion of the chosen experimental setup, its limitations, the limitations of our method, and our results

Estilos ABNT, Harvard, Vancouver, APA, etc.

Börjesson, Lukas. "Forecasting Financial Time Series through Causal and Dilated Convolutional Neural Networks". Thesis, Linköpings universitet, Institutionen för datavetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167331.

Texto completo da fonte

Resumo:

In this paper, predictions of future price movements of a major American stock index was made by analysing past movements of the same and other correlated indices. A model that has shown very good results in speech recognition was modified to suit the analysis of financial data and was then compared to a base model, restricted by assumptions made for an efficient market. The performance of any model, that is trained by looking at past observations, is heavily influenced by how the division of the data into train, validation and test sets is made. This is further exaggerated by the temporal structure of the financial data, which means that the causal relationship between the predictors and the response is dependent in time. The complexity of the financial system further increases the struggle to make accurate predictions, but the model suggested here was still able to outperform the naive base model by more than 20 percent. The model is, however, too primitive to be used as a trading system, but suitable modifications, in order to turn the model into one, will be discussed in the end of the paper.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Highlander, Tyler Clayton. "Conditional Dilated Attention Tracking Model - C-DATM". Wright State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=wright1564652134758139.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Yeh, Pin-Yi, e 葉品儀. "Multi-Scale Neural Network with Dilated Convolutions for Image Deblurring". Thesis, 2019. http://ndltd.ncl.edu.tw/handle/vgs5cw.

Texto completo da fonte

Resumo:

碩士
國立臺灣科技大學
資訊工程系
107
Several deep learning-based approaches are successful in single image deblurring, particularly, convolutional neural networks (CNN). Unlike traditional methods which try to estimate the blur kernel to extract the latent sharp image, CNN-based methods can directly find the mapping from the blurry input image to the latent sharp image. CNN usually has many layers to represent complex spatial relationships, and down-sampling layers are used to reduce the number of parameters (e.g., encoder-decoder architecture). However, down-sampling causes some spatial information to be lost, and this information could be useful in deblurring large regions. The receptive field is the spatial coverage of each feature, and increasing its value allows less loss of spatial information. We used dilated convolution to increase the receptive field of the features without increasing the number of parameters. Furthermore, the "coarse-to-fine" strategy is applied to the network to the blurry input image at different scales in this thesis. By using this strategy, we can progressively improve the outputs, and allow us to capture details from different scales, without adding more parameters. We show that the proposed model not only has better results with the state-of-the-art but also has faster execution time.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Liu, Chien-Chung, e 劉建忠. "Improved Image Super Resolution Technology Based on Dilated Convolutional Neural Network". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/w6cn2k.

Texto completo da fonte

Resumo:

碩士
國立臺中科技大學
資訊工程系碩士班
106
Image super resolution is wide application in image processing and computer vision. Because original super resolution image can’t be irreversible and it have distorted pixel values after the image is enlarged are challenging subjects. This paper proposed two architectures which is using convolutional neural network architecture of deep learning to carry out image super resolution. They estimate pixels of super resolution image by neurons of convolutional neural network. The first architecture is reduced dilated convolutional neural network. It reduces dilated convolutional neural network to six convolutional layers. In the second layer to fourth layer use convolution of double dilated rate. The first layer output concatenates the fourth layer output and the second layer output concatenates the third layer output are to deeper learning. The other is wide dilated convolutional neural network. It lets input pass convolutions of difference dilated rate to get output. It achieves wide learning. Neural network learns convolutional input of difference dilated rate by concatenating two outputs to be input of next layer at the same time. It is able to more detail feature extraction and achieve effect of wide learning. This experiments use the parameters of convolutional neural network employed dilated convolutional neural network architecture. The experimental parameters include epoch, validation split, validation mode, sub image size, sub image number, batch size. The experiments appoint appropriate parameters to be 500 epoch, 0.2 validation split, random single sub image which is sub images of the image, 41×41 sub image size, 50 sub image number, 64 batch size. Experimental results appoint PSNR of reduced dilated convolutional network higher than dilated convolutional neural network 0.13dB and strand error smaller 0.07dB. PSNR of wide dilated convolutional network higher than dilated convolutional neural network 0.08dB and strand error smaller 0.09dB. Experiments also include difference scale of image super resolution and using difference types of data sets to test difference on the two proposed architectures. Final, proposed method applied to surveillance system. Results appoint image super resolution is able to enhance part of image features. In noise is improved, image texture isn’t blurry after image super resolution.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Capítulos de livros sobre o assunto "Convolution dilatée"

Guru Pradeep Reddy, T., Kandiraju Sai Ashritha, T. M. Prajwala, G. N. Girish, Abhishek R. Kothari, Shashidhar G. Koolagudi e Jeny Rajan. "Retinal-Layer Segmentation Using Dilated Convolutions". In Proceedings of 3rd International Conference on Computer Vision and Image Processing, 279–92. Singapore: Springer Singapore, 2019. http://dx.doi.org/10.1007/978-981-32-9088-4_24.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Sun, Wei, Xijie Zhou, Xiaorui Zhang e Xiaozheng He. "A Lightweight Neural Network Combining Dilated Convolution and Depthwise Separable Convolution". In Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 210–20. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-48513-9_17.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Zhang, Jinglu, Yinyu Nie, Yao Lyu, Hailin Li, Jian Chang, Xiaosong Yang e Jian Jun Zhang. "Symmetric Dilated Convolution for Surgical Gesture Recognition". In Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, 409–18. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-59716-0_39.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Shen, Falong, e Gang Zeng. "Gaussian Dilated Convolution for Semantic Image Segmentation". In Advances in Multimedia Information Processing – PCM 2018, 324–34. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-00776-8_30.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Hu, Haigen, Chenghan Yu, Qianwei Zhou, Qiu Guan e Qi Chen. "SAMDConv: Spatially Adaptive Multi-scale Dilated Convolution". In Pattern Recognition and Computer Vision, 460–72. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-8543-2_37.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Gupta, Sachin, Priya Goyal, Bhuman Vyas, Mohammad Shabaz, Suchitra Bala e Aws Zuhair Sameen. "Dilated convolution model for lightweight neural network". In Next Generation Computing and Information Systems, 119–26. London: CRC Press, 2024. http://dx.doi.org/10.1201/9781003466383-20.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Zhang, Jing, Haiguang Li, Chao Zhang, Yangbiao Wu e Guiyi Liu. "Bearing Remaining Life Prediction Based on Temporal Convolutional Networks with Hybrid Dilated Convolutions". In Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023), 345–53. Cham: Springer Nature Switzerland, 2024. http://dx.doi.org/10.1007/978-3-031-49421-5_27.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Chen, Zhaokang, e Bertram E. Shi. "Appearance-Based Gaze Estimation Using Dilated-Convolutions". In Computer Vision – ACCV 2018, 309–24. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-20876-9_20.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Maraci, Mohammad Ali, Weidi Xie e J. Alison Noble. "Can Dilated Convolutions Capture Ultrasound Video Dynamics?" In Machine Learning in Medical Imaging, 116–24. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-00919-9_14.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Xin, Bin, Yaning Yang, Dongqing Wei e Shaoliang Peng. "CFCN: A Multi-scale Fully Convolutional Network with Dilated Convolution for Nuclei Classification and Localization". In Bioinformatics Research and Applications, 314–23. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-91415-8_27.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Trabalhos de conferências sobre o assunto "Convolution dilatée"

Liu, Jen-Yu, e Yi-Hsuan Yang. "Dilated Convolution with Dilated GRU for Music Source Separation". 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.2019/655.

Texto completo da fonte

Resumo:

Stacked dilated convolutions used in Wavenet have been shown effective for generating high-quality audios. By replacing pooling/striding with dilation in convolution layers, they can preserve high-resolution information and still reach distant locations. Producing high-resolution predictions is also crucial in music source separation, whose goal is to separate different sound sources while maintain the quality of the separated sounds. Therefore, in this paper, we use stacked dilated convolutions as the backbone for music source separation. Although stacked dilated convolutions can reach wider context than standard convolutions do, their effective receptive fields are still fixed and might not be wide enough for complex music audio signals. To reach even further information at remote locations, we propose to combine a dilated convolution with a modified GRU called Dilated GRU to form a block. A Dilated GRU receives information from k-step before instead of the previous step for a fixed k. This modification allows a GRU unit to reach a location with fewer recurrent steps and run faster because it can execute in parallel partially. We show that the proposed model with a stack of such blocks performs equally well or better than the state-of-the-art for separating both vocals and accompaniment.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Wu, Lin (Yuanbo), Deyin Liu, Xiaojie Guo, Richang Hong, Liangchen Liu e Rui Zhang. "Multi-scale Spatial Representation Learning via Recursive Hermite Polynomial Networks". In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/204.

Texto completo da fonte

Resumo:

Multi-scale representation learning aims to leverage diverse features from different layers of Convolutional Neural Networks (CNNs) for boosting the feature robustness to scale variance. For dense prediction tasks, two key properties should be satisfied: the high spatial variance across convolutional layers, and the sub-scale granularity inside a convolutional layer for fine-grained features. To pursue the two properties, this paper proposes Recursive Hermite Polynomial Networks (RHP-Nets for short). The proposed RHP-Nets consist of two major components: 1) a dilated convolution to maintain the spatial resolution across layers, and 2) a family of Hermite polynomials over a subset of dilated grids, which recursively constructs sub-scale representations to avoid the artifacts caused by naively applying the dilation convolution. The resultant sub-scale granular features are fused via trainable Hermite coefficients to form the multi-resolution representations that can be fed into the next deeper layer, and thus allowing feature interchanging at all levels. Extensive experiments are conducted to demonstrate the efficacy of our design, and reveal its superiority over state-of-the-art alternatives on a variety of image recognition tasks. Besides, introspective studies are provided to further understand the properties of our method.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Nikzad, Mohammad, Yongsheng Gao e Jun Zhou. "Attention-based Pyramid Dilated Lattice Network for Blind Image Denoising". In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. California: International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/129.

Texto completo da fonte

Resumo:

Though convolutional neural networks (CNNs) with residual and dense aggregations have obtained much attention in image denoising, they are incapable of exploiting different levels of contextual information at every convolutional unit in order to infer different levels of noise components with a single model. In this paper, to overcome this shortcoming we present a novel attention-based pyramid dilated lattice (APDL) architecture and investigate its capability for blind image denoising. The proposed framework can effectively harness the advantages of residual and dense aggregations to achieve a great trade-off between performance, parameter efficiency, and test time. It also employs a novel pyramid dilated convolution strategy to effectively capture contextual information corresponding to different noise levels through the training of a single model. Our extensive experimental investigation verifies the effectiveness and efficiency of the APDL architecture for image denoising as well as JPEG artifacts suppression tasks.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Stoller, Daniel, Mi Tian, Sebastian Ewert e Simon Dixon. "Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling". 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.2020/400.

Texto completo da fonte

Resumo:

Convolutional neural networks (CNNs) with dilated filters such as the Wavenet or the Temporal Convolutional Network (TCN) have shown good results in a variety of sequence modelling tasks. While their receptive field grows exponentially with the number of layers, computing the convolutions over very long sequences of features in each layer is time and memory-intensive, and prohibits the use of longer receptive fields in practice. To increase efficiency, we make use of the "slow feature" hypothesis stating that many features of interest are slowly varying over time. For this, we use a U-Net architecture that computes features at multiple time-scales and adapt it to our auto-regressive scenario by making convolutions causal. We apply our model ("Seq-U-Net") to a variety of tasks including language and audio generation. In comparison to TCN and Wavenet, our network consistently saves memory and computation time, with speed-ups for training and inference of over 4x in the audio generation experiment in particular, while achieving a comparable performance on real-world tasks.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Zhou, Shengwei, Caikou Chen, Guojiang Han e Xielian Hou. "Deep Convolutional Neural Network with Dilated Convolution Using Small Size Dataset". In 2019 Chinese Control Conference (CCC). IEEE, 2019. http://dx.doi.org/10.23919/chicc.2019.8865226.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Yang, Yuting, Peisong Shen e Chi Chen. "A Robust Iris Segmentation Using Fully Convolutional Network with Dilated Convolutions". In 2018 IEEE International Symposium on Multimedia (ISM). IEEE, 2018. http://dx.doi.org/10.1109/ism.2018.00010.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Gao, Jianqi, Xiangfeng Luo, Hao Wang e Zijian Wang. "Causal Event Extraction using Iterated Dilated Convolutions with Semantic Convolutional Filters". In 2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2021. http://dx.doi.org/10.1109/ictai52525.2021.00099.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

zhong Wu, Cong, Hao Dong, Xuan jie Lin, Han tong Jiang, Li quan Wang, Xin zhi Liu e Wei kai Shi. "Adaptive Filtering Remote Sensing Image Segmentation Network based on Attention Mechanism". In 10th International Conference on Information Technology Convergence and Services (ITCSE 2021). AIRCC Publishing Corporation, 2021. http://dx.doi.org/10.5121/csit.2021.110903.

Texto completo da fonte

Resumo:

It is difficult to segment small objects and the edge of the object because of larger-scale variation, larger intra-class variance of background and foreground-background imbalance in the remote sensing imagery. In convolutional neural networks, high frequency signals may degenerate into completely different ones after downsampling. We define this phenomenon as aliasing. Meanwhile, although dilated convolution can expand the receptive field of feature map, a much more complex background can cause serious alarms. To alleviate the above problems, we propose an attention-based mechanism adaptive filtered segmentation network. Experimental results on the Deepglobe Road Extraction dataset and Inria Aerial Image Labeling dataset showed that our method can effectively improve the segmentation accuracy. The F1 value on the two data sets reached 82.67% and 85.71% respectively.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Vadakkeveedu, Arjun Menon, Debabrata Mandal, Pradeep Ramachandran e Nitin Chandrachoodan. "Split-Knit Convolution: Enabling Dense Evaluation of Transpose and Dilated Convolutions on GPUs". In 2022 IEEE 29th International Conference on High Performance Computing, Data, and Analytics (HiPC). IEEE, 2022. http://dx.doi.org/10.1109/hipc56025.2022.00014.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Yang, Junyan, e Jie Jiang. "Dilated-CBAM: An Efficient Attention Network with Dilated Convolution". In 2021 IEEE International Conference on Unmanned Systems (ICUS). IEEE, 2021. http://dx.doi.org/10.1109/icus52573.2021.9641248.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Oferecemos descontos em todos os planos premium para autores cujas obras estão incluídas em seleções literárias temáticas. Contate-nos para obter um código promocional único!