Knowledge Commons of Institute of Automation,CAS
Active Universal Domain Adaptation | |
Ma, Xinhong1,2![]() ![]() ![]() | |
2021-10 | |
会议名称 | IEEE/CVF International Conference on Computer Vision (ICCV) |
会议录名称 | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
页码 | 8968-8977 |
会议日期 | 11-17 October 2019 |
会议地点 | Montreal, QC, Canada |
会议举办国 | Canada |
出版者 | Proceedings of the IEEE/CVF International Conference on Computer Vision |
摘要 | Most unsupervised domain adaptation methods rely on rich prior knowledge about the source-target label set relationship, and they cannot recognize categories beyond the source classes, which limits their applicability in practical scenarios. This paper proposes a new paradigm for unsupervised domain adaptation, termed as Active Universal Domain Adaptation (AUDA), which removes all label set assumptions and aims for not only recognizing target samples from source classes but also inferring those from target-private classes by using active learning to annotate a small budget of target data. For AUDA, it is challenging to jointly adapt the model to the target domain and select informative target samples for annotations under a large domain gap and significant semantic shift. To address the problems, we propose an Active Universal Adaptation Network (AUAN). Specifically, we first introduce Adversarial and Diverse Curriculum Learning (ADCL), which progressively aligns source and target domains to classify whether target samples are from source classes. Then, we propose a Clustering Non-transferable Gradient Embedding (CNTGE) strategy, which utilizes the clues of transferability, diversity, and uncertainty to annotate target informative sample, making it possible to infer labels for target samples of target-private classes. Finally, we propose to jointly train ADCL and CNTGE with target supervision to promote domain adaptation and target-private class recognition. Extensive experiments demonstrate that the proposed AUDA model equipped with ADCL and CNTGE achieves significant results on four popular benchmarks. |
DOI | 10.1109/ICCV48922.2021.00884 |
收录类别 | EI |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48777 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
通讯作者 | Xu, Changsheng |
作者单位 | 1.National Lab of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA) 2.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS) 3.Peng Cheng Laboratory, Shenzhen, China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Ma, Xinhong,Gao, Junyu,Xu, Changsheng. Active Universal Domain Adaptation[C]:Proceedings of the IEEE/CVF International Conference on Computer Vision,2021:8968-8977. |
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 | ||
Ma_Active_Universal_(2052KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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