Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement

ArXi:2503.06520v3 Announce Type: replace Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes. To address these limitations, we propose Seg-Zero, a novel framework that nstrates remarkable generalizability and derives explicit chain-of-thought reasoning through cognitive reinforcement. Seg-Zero