CASIA OpenIR  > 多模态人工智能系统全国重点实验室
Refined pseudo labeling for source-free domain adaptive object detection
Siqi Zhang1,2; Lu Zhang1; Zhiyong Liu1,2,3
2023-06
Conference Name2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Conference Date2023-6
Conference PlaceRhodes Island, Greece
Abstract

Domain adaptive object detection (DAOD) assumes that both labeled source data and unlabeled target data are available for training, but this assumption does not always hold in real-world scenarios. Thus, source-free DAOD is proposed to adapt the source-trained detectors to target domains with only unlabeled target data. Existing source-free DAOD methods typically utilize pseudo labeling, where the performance heavily relies on the selection of confidence threshold. However, most prior works adopt a single fixed threshold for all classes to generate pseudo labels, which ignore the imbalanced class distribution, resulting in biased pseudo labels. In this work, we propose a refined pseudo labeling framework for source-free DAOD. First, to generate unbiased pseudo labels, we present a category-aware adaptive threshold estimation module, which adaptively provides the appropriate threshold for each category. Second, to alleviate incorrect box regression, a localization-aware pseudo label assignment strategy is introduced to divide labels into certain and uncertain ones and optimize them separately. Finally, extensive experiments on four adaptation tasks demonstrate the effectiveness of our method.

Language英语
Sub direction classification目标检测、跟踪与识别
planning direction of the national heavy laboratory其他
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57278
Collection多模态人工智能系统全国重点实验室
Corresponding AuthorZhiyong Liu
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.School of Artifi cial Intelligence, University of Chinese Academy of Sciences
3.Nanjing Artifi cial Intelligence Research of IA
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Siqi Zhang,Lu Zhang,Zhiyong Liu. Refined pseudo labeling for source-free domain adaptive object detection[C],2023.
Files in This Item: Download All
File Name/Size DocType Version Access License
Zhang 等 - 2023 - Ref(17710KB)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
[Siqi Zhang]'s Articles
[Lu Zhang]'s Articles
[Zhiyong Liu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Siqi Zhang]'s Articles
[Lu Zhang]'s Articles
[Zhiyong Liu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Siqi Zhang]'s Articles
[Lu Zhang]'s Articles
[Zhiyong Liu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Zhang 等 - 2023 - Refined Pseudo Labeling for Source-Free Domain Ada.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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