A Holistically Point-guided Text Framework for Weakly-Supervised Camouflaged Object Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915097328222208 |
|---|---|
| author | Mok, Tsui Qin Gao, Shuyong Xing, Haozhe He, Miaoyang Wang, Yan Zhang, Wenqiang |
| author_facet | Mok, Tsui Qin Gao, Shuyong Xing, Haozhe He, Miaoyang Wang, Yan Zhang, Wenqiang |
| contents | Weakly-Supervised Camouflaged Object Detection (WSCOD) has gained popularity for its promise to train models with weak labels to segment objects that visually blend into their surroundings. Recently, some methods using sparsely-annotated supervision shown promising results through scribbling in WSCOD, while point-text supervision remains underexplored. Hence, this paper introduces a novel holistically point-guided text framework for WSCOD by decomposing into three phases: segment, choose, train. Specifically, we propose Point-guided Candidate Generation (PCG), where the point's foreground serves as a correction for the text path to explicitly correct and rejuvenate the loss detection object during the mask generation process (SEGMENT). We also introduce a Qualified Candidate Discriminator (QCD) to choose the optimal mask from a given text prompt using CLIP (CHOOSE), and employ the chosen pseudo mask for training with a self-supervised Vision Transformer (TRAIN). Additionally, we developed a new point-supervised dataset (P2C-COD) and a text-supervised dataset (T-COD). Comprehensive experiments on four benchmark datasets demonstrate our method outperforms state-of-the-art methods by a large margin, and also outperforms some existing fully-supervised camouflaged object detection methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06038 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Holistically Point-guided Text Framework for Weakly-Supervised Camouflaged Object Detection Mok, Tsui Qin Gao, Shuyong Xing, Haozhe He, Miaoyang Wang, Yan Zhang, Wenqiang Computer Vision and Pattern Recognition Weakly-Supervised Camouflaged Object Detection (WSCOD) has gained popularity for its promise to train models with weak labels to segment objects that visually blend into their surroundings. Recently, some methods using sparsely-annotated supervision shown promising results through scribbling in WSCOD, while point-text supervision remains underexplored. Hence, this paper introduces a novel holistically point-guided text framework for WSCOD by decomposing into three phases: segment, choose, train. Specifically, we propose Point-guided Candidate Generation (PCG), where the point's foreground serves as a correction for the text path to explicitly correct and rejuvenate the loss detection object during the mask generation process (SEGMENT). We also introduce a Qualified Candidate Discriminator (QCD) to choose the optimal mask from a given text prompt using CLIP (CHOOSE), and employ the chosen pseudo mask for training with a self-supervised Vision Transformer (TRAIN). Additionally, we developed a new point-supervised dataset (P2C-COD) and a text-supervised dataset (T-COD). Comprehensive experiments on four benchmark datasets demonstrate our method outperforms state-of-the-art methods by a large margin, and also outperforms some existing fully-supervised camouflaged object detection methods. |
| title | A Holistically Point-guided Text Framework for Weakly-Supervised Camouflaged Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.06038 |