cs.CVNov 10, 2026

ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision

Authors: Haozhan Shen, Liangbo He, Jun Lan, Huijia Zhu, Weiqiang Wang, Tiancheng Zhao, Jianwei Yin

Organizations: Ant Group · Zhejiang University · Om AI Research · Binjiang Institute of Zhejiang University

Abstract

Fine-grained visual perception requires Vision-Language Models (VLMs) to locate and interpret subtle evidence within complex scenes. Constructing supervision for this ability is challenging: questions must have correct, unambiguous answers that depend on actual fine-grained visual details rather than coarse cues or language priors. Verifying these properties makes manual annotation labor-intensive and automatic generation difficult for models that themselves struggle with fine-grained perception. Yet the same models can often recognize such details once the region is zoomed in. We exploit this global-to-zoom perception gap and introduce ZoomGain, a data construction pipeline that constructs questions about the full image from visual information gained only by zooming in. It verifies each answer on the zoomed view with multiple models, ensures that each question remains unambiguous in the full image and cannot be answered from language priors, and specifically generates high-quality distractors for multiple-choice questions. With this pipeline and human-only screening (no manual QA editing), we build ZoomGainBench, a 1,000-question bilingual benchmark on which the best of 28 VLMs achieves only 61.08. Failure analysis reveals that models favor a particular type of distractor when answering multiple-choice questions incorrectly. Beyond evaluation, training on just 9K ZoomGain samples substantially improves the visual perception capabilities of our 4B/9B models, enabling them to outperform several hundred-billion-parameter models across various perception benchmarks. The trained 9B model achieves SoTA performance on several benchmarks, such as 90.25 on HR-Bench 4K. These results establish global-to-zoom perception gaps as a practical basis for scaling fine-grained visual supervision for both evaluation and training. Our code is available at https://github.com/inclusionAI/ZoomGain.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. The Last Visible Pixel: Probing Fine-Scale Perception in Vision-Language Models

    Jun 5, 2026Lujun Li, Lama Sleem, Niccolo Gentile +4VLM EvaluationLarge Vision-Language Models

  2. Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models

    Aug 22, 2026Jinchang Zhu, Rong Fu, Yi Ding +3Large Vision-Language ModelsVisual Question Answering

  3. Look Where It Counts: A Free, Label-Free Visual Evidence Signal for Fine-Grained Vision-Language Reasoning

    Sep 21, 2026Santi Ram Tiwari, Nihal Naik, Devbrat Pandey +1Vision-Language GroundingVLM Reasoning