基于协同架构搜索和蒸馏的网络压缩

2021 4th International Conference on Artificial Intelligence for Industries (AI4I) Pub Date : 2021-09-01 DOI:10.1109/AI4I51902.2021.00018

Fanghui Xue, J. Xin

{"title":"基于协同架构搜索和蒸馏的网络压缩","authors":"Fanghui Xue, J. Xin","doi":"10.1109/AI4I51902.2021.00018","DOIUrl":null,"url":null,"abstract":"Neural Architecture Search (NAS) and its variants are competitive in many computer vision tasks lately. In this paper, we develop a Cooperative Architecture Search and Distillation (CASD) method for network compression. Compared with prior art, our method achieves better performance in ResNet164 pruning on CIFAR-10 and CIFAR-100 image classifications, promising to be extended to other tasks.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"330 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Network Compression via Cooperative Architecture Search and Distillation\",\"authors\":\"Fanghui Xue, J. Xin\",\"doi\":\"10.1109/AI4I51902.2021.00018\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neural Architecture Search (NAS) and its variants are competitive in many computer vision tasks lately. In this paper, we develop a Cooperative Architecture Search and Distillation (CASD) method for network compression. Compared with prior art, our method achieves better performance in ResNet164 pruning on CIFAR-10 and CIFAR-100 image classifications, promising to be extended to other tasks.\",\"PeriodicalId\":114373,\"journal\":{\"name\":\"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)\",\"volume\":\"330 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AI4I51902.2021.00018\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AI4I51902.2021.00018","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

近年来，神经结构搜索(NAS)及其变体在许多计算机视觉任务中具有很强的竞争力。在本文中，我们开发了一种用于网络压缩的协同架构搜索和蒸馏(CASD)方法。与现有技术相比，我们的方法在CIFAR-10和CIFAR-100图像分类上实现了更好的ResNet164剪枝性能，有望扩展到其他任务。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Network Compression via Cooperative Architecture Search and Distillation

Neural Architecture Search (NAS) and its variants are competitive in many computer vision tasks lately. In this paper, we develop a Cooperative Architecture Search and Distillation (CASD) method for network compression. Compared with prior art, our method achieves better performance in ResNet164 pruning on CIFAR-10 and CIFAR-100 image classifications, promising to be extended to other tasks.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2021 4th International Conference on Artificial Intelligence for Industries (AI4I)

自引率

0.00%

发文量