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
会议名称IEEE Computer Vision and Pattern Recognition (CVPR)
会议日期2022-6-19
会议地点New Orleans, Louisiana & Online
摘要

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.

学科领域模式识别
学科门类工学::计算机科学与技术(可授工学、理学学位)
收录类别EI
资助项目National Nature Science Foundation of China[61876086] ; National Nature Science Foundation of China[61876086]
语种英语
七大方向——子方向分类目标检测、跟踪与识别
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/47418
专题紫东太初大模型研究中心_图像与视频分析
作者单位1.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
第一作者单位模式识别国家重点实验室
推荐引用方式
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
C2AM Loss Chasing a (5757KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Tong]的文章
[Zhu, Yousong]的文章
[Chen, Yingying]的文章
百度学术
百度学术中相似的文章
[Wang, Tong]的文章
[Zhu, Yousong]的文章
[Chen, Yingying]的文章
必应学术
必应学术中相似的文章
[Wang, Tong]的文章
[Zhu, Yousong]的文章
[Chen, Yingying]的文章
相关权益政策
暂无数据
收藏/分享
文件名: C2AM Loss Chasing a Better Decision Boundary for Long-Tail Object Detection.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。