Just a Hint: Point-Supervised Camouflaged Object Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913473762426880 |
|---|---|
| author | Chen, Huafeng Shao, Dian Guo, Guangqian Gao, Shan |
| author_facet | Chen, Huafeng Shao, Dian Guo, Guangqian Gao, Shan |
| contents | Camouflaged Object Detection (COD) demands models to expeditiously and accurately distinguish objects which conceal themselves seamlessly in the environment. Owing to the subtle differences and ambiguous boundaries, COD is not only a remarkably challenging task for models but also for human annotators, requiring huge efforts to provide pixel-wise annotations. To alleviate the heavy annotation burden, we propose to fulfill this task with the help of only one point supervision. Specifically, by swiftly clicking on each object, we first adaptively expand the original point-based annotation to a reasonable hint area. Then, to avoid partial localization around discriminative parts, we propose an attention regulator to scatter model attention to the whole object through partially masking labeled regions. Moreover, to solve the unstable feature representation of camouflaged objects under only point-based annotation, we perform unsupervised contrastive learning based on differently augmented image pairs (e.g. changing color or doing translation). On three mainstream COD benchmarks, experimental results show that our model outperforms several weakly-supervised methods by a large margin across various metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10777 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Just a Hint: Point-Supervised Camouflaged Object Detection Chen, Huafeng Shao, Dian Guo, Guangqian Gao, Shan Computer Vision and Pattern Recognition Artificial Intelligence Camouflaged Object Detection (COD) demands models to expeditiously and accurately distinguish objects which conceal themselves seamlessly in the environment. Owing to the subtle differences and ambiguous boundaries, COD is not only a remarkably challenging task for models but also for human annotators, requiring huge efforts to provide pixel-wise annotations. To alleviate the heavy annotation burden, we propose to fulfill this task with the help of only one point supervision. Specifically, by swiftly clicking on each object, we first adaptively expand the original point-based annotation to a reasonable hint area. Then, to avoid partial localization around discriminative parts, we propose an attention regulator to scatter model attention to the whole object through partially masking labeled regions. Moreover, to solve the unstable feature representation of camouflaged objects under only point-based annotation, we perform unsupervised contrastive learning based on differently augmented image pairs (e.g. changing color or doing translation). On three mainstream COD benchmarks, experimental results show that our model outperforms several weakly-supervised methods by a large margin across various metrics. |
| title | Just a Hint: Point-Supervised Camouflaged Object Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2408.10777 |