ContourVLA: A Closed-Loop Perception-Action Contour Policy for Generalized Referring Expression Segmentation
ContourVLA turns Generalized Referring Expression Segmentation (GRES) into a closed-loop system where an editable contour acts as a policy state. It uses vision and language to perceive objects and geometric actions to refine the contour iteratively. This approach, enhanced by sophisticated scheduling and credit transport methods, achieves superior segmentation accuracy across multiple benchmarks.