{"title":"LE-CapsNet:一个轻型和增强胶囊网络","authors":"Pouya Shiri, A. Baniasadi","doi":"10.1109/ICMLA52953.2021.00280","DOIUrl":null,"url":null,"abstract":"Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.37% accuracy on the AffNIST dataset (compared to CapsNet’s 90.52%).","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"2 1","pages":"1767-1772"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"LE-CapsNet: A Light and Enhanced Capsule Network\",\"authors\":\"Pouya Shiri, A. Baniasadi\",\"doi\":\"10.1109/ICMLA52953.2021.00280\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.37% accuracy on the AffNIST dataset (compared to CapsNet’s 90.52%).\",\"PeriodicalId\":6750,\"journal\":{\"name\":\"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)\",\"volume\":\"2 1\",\"pages\":\"1767-1772\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICMLA52953.2021.00280\",\"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 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMLA52953.2021.00280","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.37% accuracy on the AffNIST dataset (compared to CapsNet’s 90.52%).
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
