Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approaches rely on repeated cropping or test-time visual search to introduce local evidence, but they typically do not explicitly distinguish perception from reasoning. In this paper, we propose Perceive-to-Reason (P2R), a unified framework that formulates fine-grained visual reasoning as a two-stage process: the model first localizes question-relevant evidence as a Perceiver, and then answers the question as a Reasoner base
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownVioletVision-3B →
- LinkedLinked via arxiv author · 85%Hongxing Li →
“Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning”
- LinkedLinked via arxiv author · 85%Xiufeng Huang →
“Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning”
- LinkedLinked via arxiv author · 85%Dingming Li →
“Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning”
- LinkedLinked via arxiv author · 85%Wenjing Jiang →
“Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning”
- LinkedLinked via arxiv author · 85%Zixuan Wang →
“Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning”
- LinkedLinked via arxiv author · 85%Haolei Xu →
“Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning”
- LinkedLinked via arxiv author · 85%Hanrong Zhang →
“Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning”