{"title":"DTS：利用特征稀疏性进行动态训练瘦身，实现高效卷积神经网络","authors":"Jia Yin, Wei Wang, Zhonghua Guo, Yangchun Ji","doi":"10.1007/s11554-024-01511-y","DOIUrl":null,"url":null,"abstract":"<p>Deep convolutional neural networks have achieved remarkable progress on computer vision tasks over last years. In this paper, we proposed a dynamic training slimming with feature sparsity based on structured pruning, named DTS, for efficient and automatic channel pruning. Unlike other existing pruning methods, which require manual intervention for pruning settings for each layer, DTS can design suitable architecture width for target datasets and deployment resources by automated pruning. The proposed method can be deployed to modern CNNs and the experimental results on CIFAR, ImageNet and PASCAL VOC benchmark datasets demonstrate the effectiveness of the proposed method, which significantly exceeds the other schemes.</p>","PeriodicalId":51224,"journal":{"name":"Journal of Real-Time Image Processing","volume":"20 1","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DTS: dynamic training slimming with feature sparsity for efficient convolutional neural network\",\"authors\":\"Jia Yin, Wei Wang, Zhonghua Guo, Yangchun Ji\",\"doi\":\"10.1007/s11554-024-01511-y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Deep convolutional neural networks have achieved remarkable progress on computer vision tasks over last years. In this paper, we proposed a dynamic training slimming with feature sparsity based on structured pruning, named DTS, for efficient and automatic channel pruning. Unlike other existing pruning methods, which require manual intervention for pruning settings for each layer, DTS can design suitable architecture width for target datasets and deployment resources by automated pruning. The proposed method can be deployed to modern CNNs and the experimental results on CIFAR, ImageNet and PASCAL VOC benchmark datasets demonstrate the effectiveness of the proposed method, which significantly exceeds the other schemes.</p>\",\"PeriodicalId\":51224,\"journal\":{\"name\":\"Journal of Real-Time Image Processing\",\"volume\":\"20 1\",\"pages\":\"\"},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2024-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Real-Time Image Processing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s11554-024-01511-y\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Real-Time Image Processing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11554-024-01511-y","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
DTS: dynamic training slimming with feature sparsity for efficient convolutional neural network
Deep convolutional neural networks have achieved remarkable progress on computer vision tasks over last years. In this paper, we proposed a dynamic training slimming with feature sparsity based on structured pruning, named DTS, for efficient and automatic channel pruning. Unlike other existing pruning methods, which require manual intervention for pruning settings for each layer, DTS can design suitable architecture width for target datasets and deployment resources by automated pruning. The proposed method can be deployed to modern CNNs and the experimental results on CIFAR, ImageNet and PASCAL VOC benchmark datasets demonstrate the effectiveness of the proposed method, which significantly exceeds the other schemes.
期刊介绍：
Due to rapid advancements in integrated circuit technology, the rich theoretical results that have been developed by the image and video processing research community are now being increasingly applied in practical systems to solve real-world image and video processing problems. Such systems involve constraints placed not only on their size, cost, and power consumption, but also on the timeliness of the image data processed.
Examples of such systems are mobile phones, digital still/video/cell-phone cameras, portable media players, personal digital assistants, high-definition television, video surveillance systems, industrial visual inspection systems, medical imaging devices, vision-guided autonomous robots, spectral imaging systems, and many other real-time embedded systems. In these real-time systems, strict timing requirements demand that results are available within a certain interval of time as imposed by the application.
It is often the case that an image processing algorithm is developed and proven theoretically sound, presumably with a specific application in mind, but its practical applications and the detailed steps, methodology, and trade-off analysis required to achieve its real-time performance are not fully explored, leaving these critical and usually non-trivial issues for those wishing to employ the algorithm in a real-time system.
The Journal of Real-Time Image Processing is intended to bridge the gap between the theory and practice of image processing, serving the greater community of researchers, practicing engineers, and industrial professionals who deal with designing, implementing or utilizing image processing systems which must satisfy real-time design constraints.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
