Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2503.22180 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913763714662400 |
|---|---|
| author | Guan, Juwei Fang, Xiaolin Kim, Donghyun Gong, Haotian Zhu, Tongxin Ling, Zhen Yang, Ming |
| author_facet | Guan, Juwei Fang, Xiaolin Kim, Donghyun Gong, Haotian Zhu, Tongxin Ling, Zhen Yang, Ming |
| contents | Low-quality data often suffer from insufficient image details, introducing an extra implicit aspect of camouflage that complicates camouflaged object detection (COD). Existing COD methods focus primarily on high-quality data, overlooking the challenges posed by low-quality data, which leads to significant performance degradation. Therefore, we propose KRNet, the first framework explicitly designed for COD on low-quality data. KRNet presents a Leader-Follower framework where the Leader extracts dual gold-standard distributions: conditional and hybrid, from high-quality data to drive the Follower in rectifying knowledge learned from low-quality data. The framework further benefits from a cross-consistency strategy that improves the rectification of these distributions and a time-dependent conditional encoder that enriches the distribution diversity. Extensive experiments on benchmark datasets demonstrate that KRNet outperforms state-of-the-art COD methods and super-resolution-assisted COD approaches, proving its effectiveness in tackling the challenges of low-quality data in COD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22180 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Knowledge Rectification for Camouflaged Object Detection: Unlocking Insights from Low-Quality Data Guan, Juwei Fang, Xiaolin Kim, Donghyun Gong, Haotian Zhu, Tongxin Ling, Zhen Yang, Ming Computer Vision and Pattern Recognition Low-quality data often suffer from insufficient image details, introducing an extra implicit aspect of camouflage that complicates camouflaged object detection (COD). Existing COD methods focus primarily on high-quality data, overlooking the challenges posed by low-quality data, which leads to significant performance degradation. Therefore, we propose KRNet, the first framework explicitly designed for COD on low-quality data. KRNet presents a Leader-Follower framework where the Leader extracts dual gold-standard distributions: conditional and hybrid, from high-quality data to drive the Follower in rectifying knowledge learned from low-quality data. The framework further benefits from a cross-consistency strategy that improves the rectification of these distributions and a time-dependent conditional encoder that enriches the distribution diversity. Extensive experiments on benchmark datasets demonstrate that KRNet outperforms state-of-the-art COD methods and super-resolution-assisted COD approaches, proving its effectiveness in tackling the challenges of low-quality data in COD. |
| title | Knowledge Rectification for Camouflaged Object Detection: Unlocking Insights from Low-Quality Data |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22180 |