Conditional Diffusion for Interactive Segmentation

In click-based interactive segmentation, the mask extraction process is dictated by positive/negative user clicks; however, most existing methods do not fully exploit the user cues, requiring excessive numbers of clicks for satisfactory results. We propose Conditional Diffusion Network (CDNet), which propagates labeled representations from clicks to conditioned destinations with two levels of affinities: Feature Diffusion Module (FDM) spreads features from clicks to potential target regions with global similarity; Pixel Diffusion Module (PDM) diffuses the predicted logits of clicks within locally connected regions. Thus, the information inferred by user clicks could be generalized to proper destinations. In addition, we put forward Diversified Training (DT), which reduces the optimization ambiguity caused by click simulation. With FDM,PDM and DT, CD-Net could better understand user's intentions and make better predictions with limited interactions. CDNet achieves state-of-the-art performance on several benchmarks.