Source-Free Domain Adaptive Object Detection with Semantics Compensation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914068687749120 |
|---|---|
| author | Tang, Song Yang, Jiuzheng Ye, Mao Wang, Boyu Gan, Yan Zhu, Xiatian |
| author_facet | Tang, Song Yang, Jiuzheng Ye, Mao Wang, Boyu Gan, Yan Zhu, Xiatian |
| contents | Strong data augmentation is a fundamental component of state-of-the-art mean teacher-based Source-Free domain adaptive Object Detection (SFOD) methods, enabling consistency-based self-supervised optimization along weak augmentation. However, our theoretical analysis and empirical observations reveal a critical limitation: strong augmentation can inadvertently erase class-relevant components, leading to artificial inter-category confusion. To address this issue, we introduce Weak-to-strong Semantics Compensation (WSCo), a novel remedy that leverages weakly augmented images, which preserve full semantics, as anchors to enrich the feature space of their strongly augmented counterparts. Essentially, this compensates for the class-relevant semantics that may be lost during strong augmentation on the fly. Notably, WSCo can be implemented as a generic plug-in, easily integrable with any existing SFOD pipelines. Extensive experiments validate the negative impact of strong augmentation on detection performance, and the effectiveness of WSCo in enhancing the performance of previous detection models on standard benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05557 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Source-Free Domain Adaptive Object Detection with Semantics Compensation Tang, Song Yang, Jiuzheng Ye, Mao Wang, Boyu Gan, Yan Zhu, Xiatian Computer Vision and Pattern Recognition Strong data augmentation is a fundamental component of state-of-the-art mean teacher-based Source-Free domain adaptive Object Detection (SFOD) methods, enabling consistency-based self-supervised optimization along weak augmentation. However, our theoretical analysis and empirical observations reveal a critical limitation: strong augmentation can inadvertently erase class-relevant components, leading to artificial inter-category confusion. To address this issue, we introduce Weak-to-strong Semantics Compensation (WSCo), a novel remedy that leverages weakly augmented images, which preserve full semantics, as anchors to enrich the feature space of their strongly augmented counterparts. Essentially, this compensates for the class-relevant semantics that may be lost during strong augmentation on the fly. Notably, WSCo can be implemented as a generic plug-in, easily integrable with any existing SFOD pipelines. Extensive experiments validate the negative impact of strong augmentation on detection performance, and the effectiveness of WSCo in enhancing the performance of previous detection models on standard benchmarks. |
| title | Source-Free Domain Adaptive Object Detection with Semantics Compensation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.05557 |