CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection
Wang, Tong1,2; Zhu, Yousong1; Chen, Yingying1; Zhao, Chaoyang1,4; Yu, Bin1,2; Wang, Jinqiao1,2,3; Tang, Ming1
2022-06
Conference NameIEEE Computer Vision and Pattern Recognition (CVPR)
Conference Date2022-6-19
Conference PlaceNew Orleans, Louisiana & Online
Abstract

Long-tail object detection suffers from poor performance on tail categories. We reveal that the real culprit lies in the extremely imbalanced distribution of the classifier’s weight norm. For conventional softmax cross-entropy loss, such imbalanced weight norm distribution yields ill-conditioned decision boundary for categories which have small weight
norms. To get rid of this situation, we choose to maximize the cosine similarity between the learned feature and the weight vector of target category rather than the innerproduct of them. The decision boundary between any two categories is the angular bisector of their weight vectors.
Whereas, the absolutely equal decision boundary is suboptimal because it reduces the model’s sensitivity to various categories. Intuitively, categories with rich data diversity should occupy a larger area in the classification space while categories with limited data diversity should occupy a slightly small space. Hence, we devise a Category-Aware
Angular Margin Loss (C2AM Loss) to introduce an adaptive angular margin between any two categories. Specifically, the margin between two categories is proportional to the ratio of their classifiers’ weight norms. As a result, the decision boundary is slightly pushed towards the category which has a smaller weight norm. We conduct comprehensive experiments on LVIS dataset. C2AM Loss brings 4.9∼5.2 AP improvements on different detectors and backbones compared with baseline.

Subject Area模式识别
MOST Discipline Catalogue工学::计算机科学与技术(可授工学、理学学位)
Indexed ByEI
Funding ProjectNational Nature Science Foundation of China[61876086] ; National Nature Science Foundation of China[61876086]
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/47418
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
3.Peng Cheng Laboratory, Shenzhen, China
4.Development Research Institute of Guangzhou Smart City, Guangzhou, China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Wang, Tong,Zhu, Yousong,Chen, Yingying,et al. C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
C2AM Loss Chasing a (5757KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Tong]'s Articles
[Zhu, Yousong]'s Articles
[Chen, Yingying]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Tong]'s Articles
[Zhu, Yousong]'s Articles
[Chen, Yingying]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Tong]'s Articles
[Zhu, Yousong]'s Articles
[Chen, Yingying]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: C2AM Loss Chasing a Better Decision Boundary for Long-Tail Object Detection.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.