Problem
Research questions and friction points this paper is trying to address.
Fine-grained Perception
Resolution Requirements
Token Compression
Region of Interest (RoI)
Cost Reduction
Region-Level Policy Optimization for Fine-grained MLLM Perception
🤖 AI Summary
为解决提高分辨率带来的成本问题，本文提出一种基于区域级强化学习的方法Vision-RL2，通过优化轻量级提案网络来实现细粒度MLLM感知。
📝 Abstract
Fine-grained visual perception in MLLMs is commonly improved by raising the resolution, but the added visual tokens inflate vision-encoding and language-model prefilling costs. We show that the two operations underlying fine-grained perception, localizing the region of interest (RoI) and recognizing its content, have different resolution requirements. In a controlled diagnostic, localization tolerates roughly 3 to 4 times stronger token compression than recognition, which motivates localizing from a coarse view and concentrating resolution on the selected evidence. Decoding coordinates with the MLLM can be trained end-to-end from answers, but costs a full model pass per query and depends on grounding ability. A lightweight proposal network distilled from the model's attention is fast, but inherits the noise of its attention targets. The RoI from the proposal network reaches the answer through a discrete region choice, so its faithfulness to the answer cannot supervise the network. We therefore optimize the proposal network with region-level reinforcement learning, which we call Vision-RL2. It treats coherent regions as actions, and a frozen MLLM reader scores each one by how its removal changes the answer likelihood. Complementary subtractive and additive objectives suppress distracting proposals and recover missing evidence, updating only the predictor without region annotations, response sampling, or reasoning trajectories. The refined proposal further enables a sparse encoding that magnifies evidence and excludes background tokens. Across six fine-grained benchmarks and four MLLM backbones, Vision-RL2 improves accuracy over the base model at every token budget and surpasses its largest-budget accuracy with about 4 times fewer visual tokens. Code is available at https://github.com/YuHengsss/VisionRL2 .
Innovation
Methods, ideas, or system contributions that make the work stand out.
region-level reinforcement learning
fine-grained visual perception
token compression
proposal network
🔎 Similar Papers
No similar papers found.
