CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Adaptive Class Suppression Loss for Long-Tail Object Detection
Wang, Tong1,2; Zhu, Yousong1,3; Zhao, Chaoyang1; Zeng, Wei4,5; Wang, Jinqiao1,2,6; Tang, Ming1
2021-06
Conference NameIEEE/CVF Conference on Computer Vision and Pattern Recognition
Pages3103-3112
Conference Date2021-6-19
Conference PlaceOnline
Abstract

To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies. These methods bring the following two problems. One is the training inconsistency between adjacent categories of similar sizes,
and the other is that the learned model is lack of discrimination for tail categories which are semantically similar to some of the head categories. In this paper, we devise a novel Adaptive Class Suppression Loss (ACSL) to effectively tackle the above problems and improve the detection performance of tail categories. Specifically, we introduce a statistic-free perspective to analyze the long-tail distribution, breaking the limitation of manual grouping. According to this perspective, our ACSL adjusts the suppression gradients for each sample of each class adaptively, ensuring the training consistency and boosting the discrimination for rare categories. Extensive experiments on long-tail datasets LVIS and Open Images show that the our ACSL achieves 5.18% and 5.2% improvements with ResNet50-FPN, and sets a new state of the art. Code and models are available at https://github.com/CASIA-IVA-Lab/ACSL.
 

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 Natural Science Foundation of China (NSFC)[61633002] ; National Natural Science Foundation of China[61806200] ; National Nature Science Foundation of China[61876086] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61772527] ; National Nature Science Foundation of China[61876086] ; National Natural Science Foundation of China[61806200] ; National Natural Science Foundation of China (NSFC)[61633002]
Language英语
Sub direction classification目标检测、跟踪与识别
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/47413
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.ObjectEye Inc., Beijing, China
4.Peking University, Beijing, China
5.Peng Cheng Laboratory, Shenzhen, China
6.NEXWISE Co., Ltd., 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,Zhao, Chaoyang,et al. Adaptive Class Suppression Loss for Long-Tail Object Detection[C],2021:3103-3112.
Files in This Item: Download All
File Name/Size DocType Version Access License
Adaptive Class Suppr(2668KB)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
[Zhao, Chaoyang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Tong]'s Articles
[Zhu, Yousong]'s Articles
[Zhao, Chaoyang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Tong]'s Articles
[Zhu, Yousong]'s Articles
[Zhao, Chaoyang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Adaptive Class Suppression Loss 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.