GEAR-Seg: 推論セグメンテーションとデータエンジンのための根拠付き説明可能エージェント
GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine
推論セグメンテーションを、クラス非依存セグメンテーション、意味記述、LLM推論に分離した説明可能なエージェントを提案し、ゼロショットで高性能を達成。さらに、大規模データセットGEAR-131Kを自動生成し、軽量モデルの蒸留実験で有効性を示した。
著者: Yanan Wang, Wen Li, Yibin Ying, Zhenghao Fei
分類: cs.CV
原文アブストラクト
Reasoning segmentation requires localizing targets based on complex, implicit queries. Current end-to-end models typically entangle perception and deduction into an opaque black box, severely limiting interpretability and scalability. To address this, we propose GEAR-Seg (Grounded Explainable Agent for Reasoning Segmentation), an explicitly decoupled agent that shifts the paradigm by translating visual pixels into dense, attribute-rich text. By decoupling class-agnostic segmentation, semantic description, and Large Language Model (LLM) deduction, GEAR-Seg transforms implicit reasoning into an explicit, trackable logic chain. As a zero-shot inference framework, it achieves highly competitive performance across diverse reasoning and fine-grained referring segmentation benchmarks. Furthermore, GEAR-Seg inherently functions as a highly scalable data engine. Utilizing this engine, we construct GEAR-131K, a massive benchmark (over 38k images, 656k QA-mask pairs) introducing a multifaceted taxonomy tailored for complex real-world manipulation-oriented reasoning. Finally, distillation experiments demonstrate that lightweight models supervised exclusively by our automated pipeline closely match the upper-bound performance of costly human-annotated baselines.