{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/seg-zero-reasoning-chain-guided-segmentation","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","arxiv_id":"2503.06520","date":"2025-03-09","proceeding":null,"authors":["Yuqi Liu","Bohao Peng","Zhisheng Zhong","Zihao Yue","Fanbin Lu","Bei Yu","Jiaya Jia"],"abstract":"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 demonstrates remarkable generalizability and derives explicit chain-of-thought reasoning through cognitive reinforcement. Seg-Zero introduces a decoupled architecture consisting of a reasoning model and a segmentation model. The reasoning model interprets user intentions, generates explicit reasoning chains, and produces positional prompts, which are subsequently used by the segmentation model to generate precious pixel-level masks. We design a sophisticated reward mechanism that integrates both format and accuracy rewards to effectively guide optimization directions. Trained exclusively via reinforcement learning with GRPO and without explicit reasoning data, Seg-Zero achieves robust zero-shot generalization and exhibits emergent test-time reasoning capabilities. Experiments show that Seg-Zero-7B achieves a zero-shot performance of 57.5 on the ReasonSeg benchmark, surpassing the prior LISA-7B by 18\\%. This significant improvement highlights Seg-Zero's ability to generalize across domains while presenting an explicit reasoning process. Code is available at https://github.com/dvlab-research/Seg-Zero.","url_abs":"https://arxiv.org/abs/2503.06520v1","url_pdf":"https://arxiv.org/pdf/2503.06520v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"seg-zero-reasoning-chain-guided-segmentation","repo_url":"https://github.com/dvlab-research/Seg-Zero","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"seg-zero-reasoning-chain-guided-segmentation","repo_url":"https://github.com/dvlab-research/VisionReasoner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"seg-zero-reasoning-chain-guided-segmentation","repo_url":"https://github.com/hiyouga/easyr1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open Vocabulary Object Detection"},{"task_slug":"open-vocabulary-semantic-segmentation","task_name":"Open Vocabulary Semantic Segmentation"},{"task_slug":"reasoning-segmentation","task_name":"Reasoning Segmentation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"zero-shot-segmentation","task_name":"Zero Shot Segmentation"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.06520","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}