Long-Tailed Visual Recognition via Improved Cross-Window Self-Attention and TrivialAugment
文献类型:期刊论文
作者 | Song, Ying2,3,4; Li, Mengxing2,3; Wang, Bo1 |
刊名 | IEEE ACCESS
![]() |
出版日期 | 2023 |
卷号 | 11页码:49601-49610 |
关键词 | Convolutional neural networks Continuous wavelet transforms Data models Training Computer vision Transformers Transfer learning Long-tailed recognition self-attention vision transformer CNN TrivialAugment |
ISSN号 | 2169-3536 |
DOI | 10.1109/ACCESS.2023.3277204 |
英文摘要 | In the real world, large-scale image data sets usually present long-tailed distribution. When traditional visual recognition methods are applied to long-tail image data sets, problems such as model failure and sudden decline in recognition accuracy occur. While, when deep learning models encounter long-tailed datasets, they tend to perform poorly. In order to mitigate the impact of these problems, we propose CWTA (Long-tailed Visual Recognition via improved Cross-Window Self-Attention and TrivialAugment). CWTA uses CNN to better capture the local features of the image, uses the Cross-Window Self-Attention mechanism to dynamically adjust the perception domain to better deal with image noise, and uses TrivialAugment to enhance the diversity of a few types of data samples, thus improving the recognition accuracy of long-tailed distributed images. The experimental results show that the proposed CWTA performs best in the classification accuracy of different categories on different long-tailed datasets. We also compared CWTA with other long-tailed recognition algorithms (such as OLTR, LWS, ResLT, PaCo, and BALLAD), and the CWTA is the best when ResNet-50 as the Backbone. On the CIFAR100-LT, ImageNet-LT, and Places-LT datasets, the acc of all categories of CWTA is 12.9%, 0.4%, and 1.3% higher than that of BALLAD, respectively. For F-1-Score on CIFAR100-LT, ImageNet-LT, and Places-LT datasets, CWTA is 6.6%, 2.2%, and 1.5% higher than BALLAD, respectively. |
资助项目 | National Natural Science Foundation of China[61872043] ; State Key Laboratory of Computer Architecture, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)[CARCHA202103] |
WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
语种 | 英语 |
WOS记录号 | WOS:001005708800001 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
源URL | [http://119.78.100.204/handle/2XEOYT63/21193] ![]() |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Song, Ying |
作者单位 | 1.Zhengzhou Univ Light Ind, Software Engn Coll, Zhengzhou 450002, Peoples R China 2.Beijing Informat Sci & Technol Univ, Beijing Key Lab Internet Culture & Digital Dissemi, Beijing 100101, Peoples R China 3.Beijing Informat Sci & Technol Univ, Beijing Adv Innovat Ctr Mat Genome Engn, Beijing 100101, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100086, Peoples R China |
推荐引用方式 GB/T 7714 | Song, Ying,Li, Mengxing,Wang, Bo. Long-Tailed Visual Recognition via Improved Cross-Window Self-Attention and TrivialAugment[J]. IEEE ACCESS,2023,11:49601-49610. |
APA | Song, Ying,Li, Mengxing,&Wang, Bo.(2023).Long-Tailed Visual Recognition via Improved Cross-Window Self-Attention and TrivialAugment.IEEE ACCESS,11,49601-49610. |
MLA | Song, Ying,et al."Long-Tailed Visual Recognition via Improved Cross-Window Self-Attention and TrivialAugment".IEEE ACCESS 11(2023):49601-49610. |
入库方式: OAI收割
来源:计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。