Knowledge Commons of Institute of Automation,CAS
Refined pseudo labeling for source-free domain adaptive object detection | |
Siqi Zhang1,2; Lu Zhang1; Zhiyong Liu1,2,3 | |
2023-06 | |
会议名称 | 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
会议日期 | 2023-6 |
会议地点 | Rhodes Island, Greece |
摘要 | 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. |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 其他 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57278 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zhiyong Liu |
作者单位 | 1.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 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Siqi Zhang,Lu Zhang,Zhiyong Liu. Refined pseudo labeling for source-free domain adaptive object detection[C],2023. |
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 | ||
Zhang 等 - 2023 - Ref(17710KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论