Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911002166034432 |
|---|---|
| author | Shen, Yuqi Xiao, Fengyang Hu, Sujie Pang, Youwei Pu, Yifan Fang, Chengyu Li, Xiu He, Chunming |
| author_facet | Shen, Yuqi Xiao, Fengyang Hu, Sujie Pang, Youwei Pu, Yifan Fang, Chengyu Li, Xiu He, Chunming |
| contents | Camouflaged Object Detection (COD) presents inherent challenges due to the subtle visual differences between targets and their backgrounds. While existing methods have made notable progress, there remains significant potential for post-processing refinement that has yet to be fully explored. To address this limitation, we propose the Uncertainty-Masked Bernoulli Diffusion (UMBD) model, the first generative refinement framework specifically designed for COD. UMBD introduces an uncertainty-guided masking mechanism that selectively applies Bernoulli diffusion to residual regions with poor segmentation quality, enabling targeted refinement while preserving correctly segmented areas. To support this process, we design the Hybrid Uncertainty Quantification Network (HUQNet), which employs a multi-branch architecture and fuses uncertainty from multiple sources to improve estimation accuracy. This enables adaptive guidance during the generative sampling process. The proposed UMBD framework can be seamlessly integrated with a wide range of existing Encoder-Decoder-based COD models, combining their discriminative capabilities with the generative advantages of diffusion-based refinement. Extensive experiments across multiple COD benchmarks demonstrate consistent performance improvements, achieving average gains of 5.5% in MAE and 3.2% in weighted F-measure with only modest computational overhead. Code will be released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10712 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement Shen, Yuqi Xiao, Fengyang Hu, Sujie Pang, Youwei Pu, Yifan Fang, Chengyu Li, Xiu He, Chunming Computer Vision and Pattern Recognition Camouflaged Object Detection (COD) presents inherent challenges due to the subtle visual differences between targets and their backgrounds. While existing methods have made notable progress, there remains significant potential for post-processing refinement that has yet to be fully explored. To address this limitation, we propose the Uncertainty-Masked Bernoulli Diffusion (UMBD) model, the first generative refinement framework specifically designed for COD. UMBD introduces an uncertainty-guided masking mechanism that selectively applies Bernoulli diffusion to residual regions with poor segmentation quality, enabling targeted refinement while preserving correctly segmented areas. To support this process, we design the Hybrid Uncertainty Quantification Network (HUQNet), which employs a multi-branch architecture and fuses uncertainty from multiple sources to improve estimation accuracy. This enables adaptive guidance during the generative sampling process. The proposed UMBD framework can be seamlessly integrated with a wide range of existing Encoder-Decoder-based COD models, combining their discriminative capabilities with the generative advantages of diffusion-based refinement. Extensive experiments across multiple COD benchmarks demonstrate consistent performance improvements, achieving average gains of 5.5% in MAE and 3.2% in weighted F-measure with only modest computational overhead. Code will be released. |
| title | Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.10712 |