Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement
This work addresses the challenge of improving detection accuracy in camouflaged object detection, an incremental refinement for computer vision applications.
The paper tackled the problem of refining camouflaged object detection by proposing the Uncertainty-Masked Bernoulli Diffusion model, which selectively applies diffusion to poor-quality regions, resulting in average gains of 5.5% in MAE and 3.2% in weighted F-measure across benchmarks.
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.