Frequency-based pseudo-domain generation for domain generalizable object detection
文献类型：期刊论文
| 作者 | Zhang, Siqi2,3 ; Zhang, Lu2; Liu, Zhi-Yong1,2,3
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2023-07-14 |
| 卷号 | 542页码:12 |
| 关键词 | Domain generalization Object detection Transfer learning Self-Supervised learning |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2023.126265 |
| 通讯作者 | Liu, Zhi-Yong(zhiyong.liu@ia.ac.cn) |
| 英文摘要 | Domain generalizable object detection (DGOD) aims to train a detector that performs well on multiple unseen target domains, which is crucial for deploying the detector in practice. Recent methods for DGOD typically inherit the idea from domain adaptation to align or disentangle features, but these meth-ods struggle to handle unknown target distributions. In this paper, we propose a unified framework to tackle the DGOD task from a novel pseudo-domain generation perspective. Our framework comprises two stages: distribution diversification and domain-invariant feature learning. In the distribution diver-sification stage, we design a Frequency-based Pseudo-domain Generator (FPG) to construct the pseudo domain via excavating latent style information and enhancing semantic information in frequency space. The generated pseudo domain can provide diverse training distributions, which enhances generalization performance. In the domain-invariant feature learning stage, we introduce Rotation Prediction and Semantic Consistency (RPSC) learning, including an auxiliary self-supervised task rotation prediction to encourage generalized feature learning and a semantic consistency loss to enforce the detector to be invariant of domain shifts. Extensive experiments are conducted on various object detection benchmarks, demonstrating the superiority of our approach over state-of-the-art methods in both single-source and multi-source settings.(c) 2023 Elsevier B.V. All rights reserved. |
| WOS关键词 | ADAPTATION |
| 资助项目 | National Key Research and Development Plan of China[2020AAA0108902] ; Strategic Priority Research Program of Chinese Acad- emy of Sciences[XDB32050100] ; NSFC[62206288] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001003715300001 |
| 出版者 | ELSEVIER |
| 资助机构 | National Key Research and Development Plan of China ; Strategic Priority Research Program of Chinese Acad- emy of Sciences ; NSFC |
| 源URL | [http://ir.ia.ac.cn/handle/173211/53420]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Liu, Zhi-Yong |
| 作者单位 | 1.Nanjing Artificial Intelligence Res IA, Nanjing 211100, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Siqi,Zhang, Lu,Liu, Zhi-Yong. Frequency-based pseudo-domain generation for domain generalizable object detection[J]. NEUROCOMPUTING,2023,542:12. |
| APA | Zhang, Siqi,Zhang, Lu,&Liu, Zhi-Yong.(2023).Frequency-based pseudo-domain generation for domain generalizable object detection.NEUROCOMPUTING,542,12. |
| MLA | Zhang, Siqi,et al."Frequency-based pseudo-domain generation for domain generalizable object detection".NEUROCOMPUTING 542(2023):12. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。