Proceedings of the Third International Symposium on Computer Vision and the Internet最新文献_第3页

Video Retrieval based on Patterns of Oriented Edge Magnitude 基于有向边缘大小模式的视频检索

Proceedings of the Third International Symposium on Computer Vision and the Internet Pub Date : 2016-09-21 DOI: 10.1145/2983402.2983433

K. R. Holla, B. H. Shekar

引用次数: 1

Progressive Image Denoising using Fast Noise Variance Estimation 基于快速噪声方差估计的渐进图像去噪

Proceedings of the Third International Symposium on Computer Vision and the Internet Pub Date : 2016-09-21 DOI: 10.1145/2983402.2983440

B. K. Thote, K. Jondhale

引用次数: 1

Deep Residual Networks with Exponential Linear Unit 指数线性单元深度残差网络

Proceedings of the Third International Symposium on Computer Vision and the Internet Pub Date : 2016-04-14 DOI: 10.1145/2983402.2983406

Anish Shah, Eashan Kadam, Hena Shah, Sameer Shinde

{"title":"Deep Residual Networks with Exponential Linear Unit","authors":"Anish Shah, Eashan Kadam, Hena Shah, Sameer Shinde","doi":"10.1145/2983402.2983406","DOIUrl":"https://doi.org/10.1145/2983402.2983406","url":null,"abstract":"The depth of convolutional neural networks is a crucial ingredient for reduction in test errors on benchmarks like ImageNet and COCO. However, training a neural network becomes difficult with increasing depth. Problems like vanishing gradient and diminishing feature reuse are quite trivial in very deep convolutional neural networks. The notable recent contributions towards solving these problems and simplifying the training of very deep models are Residual and Highway Networks. These networks allow earlier representations (from the input or those learned in earlier layers) to flow unimpededly to later layers through skip connections. Such very deep models with hundreds or more layers have lead to a considerable decrease in test errors, on benchmarks like ImageNet and COCO. In this paper, we propose to replace the combination of ReLU and Batch Normalization with Exponential Linear Unit (ELU) in Residual Networks. Our experiments show that this not only speeds up the learning behavior in Residual Networks, but also improves the classification performance as the depth increases. Our model increases the accuracy on datasets like CIFAR-10 and CIFAR-100 by a significant margin.","PeriodicalId":283626,"journal":{"name":"Proceedings of the Third International Symposium on Computer Vision and the Internet","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127830315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 103

Proceedings of the Third International Symposium on Computer Vision and the Internet 第三届计算机视觉与互联网国际学术研讨会论文集

Proceedings of the Third International Symposium on Computer Vision and the Internet Pub Date : 1900-01-01 DOI: 10.1145/2983402

引用次数: 12