ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision
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
| Benchmark | #Questions | QA authoring | Language | Evidence | Blind filter | Local verif. | Dual-view | Dedicated distractor generation |
|---|---|---|---|---|---|---|---|---|
| ZoomBench Wei et al. (2026) | 845 | Model+Human | EN | Auto | ✗ | ✗ | ✓ | ✗ |
| V* Bench Wu and Xie (2023) | 191 | Human | EN | Human | ✗ | ✗ | ✗ | ✗ |
| HR-Bench Wang et al. (2025b) | 200 | Model+Human | EN | ✗ | ✗ | ✗ | ✗ | ✗ |
| VisualProbe Lai et al. (2025) | 500 | – | EN | ✗ | ✗ | ✗ | ✗ | N/A |
| TreeBench Wang et al. (2025a) | 405 | Model+Human | EN | Human | ✗ | ✗ | ✗ | ✗ |
| FINERS-4k Zhang et al. (2026b) | 2,427 | Human | EN | – | ✗ | ✗ | ✗ | ✗ |
| English | Chinese | Overall | |||||||
| Model | Attr | Count | OCR | Overall | Attr | Count | OCR | Overall | |
| Closed-source Frontier VLMs | |||||||||
| GPT-5.5 OpenAI () | 52.75 | 57.45 | 60.40 | 56.51 | 52.12 | 63.83 | 60.96 | 57.06 | 56.79 |
| Gemini-3.6-Flash Google DeepMind (2026) | 51.27 | 42.55 | 74.71 | 60.62 | 48.52 | 45.74 | 71.42 | 58.20 | 59.41 |
| Claude-Opus-5 Anthropic (2026) | 48.09 | 63.83 | 71.86 | 59.89 | 48.73 | 62.77 | 71.29 | 59.84 | 59.86 |
| GPT-5.6-Sol OpenAI () | 56.57 | 62.77 | 67.93 | 62.08 | 54.03 | 63.83 | 65.84 | 60.07 | 61.08 |
| Held-in | Fine-grained Perception | General Perception | Difficult Percept & Reason | ||||||||||||
| Model | ZoomGain Bench | Zoom Bench | V* Bench | HR 4K | HR 8K | MME-RW Lite | Tree Bench | Visual Probe | CV- Bench | MMStar | MMVP | Baby Vision | Perception Bench | O3- Bench | Avg. Only Held-out |
| Several Large Parameter VLMs | |||||||||||||||
| GPT-5.1 | 23.22 | 47.22 | 70.16 | 67.00 | 65.25 | 45.86 | 47.65 | 29.90 | 84.22 | 71.60 | 32.67 | 13.92 | 28.97 | 31.01 | 48.88 |
| Qwen3-VL-235B-A22B | 40.51 | 49.11 | 87.96 | 84.50 | 81.62 | 58.16 | 53.58 | 46.41 | 86.72 | 76.33 | 64.00 | 18.30 | 35.50 | 60.58 | 61.75 |
| Qwen3.5-122B-A10B | 41.11 | 51.83 | 84.82 | 86.50 | 83.75 | 57.89 | 54.07 | 44.85 | 88.06 | 74.60 | 70.00 | 19.07 | 38.80 | 65.22 | 63.04 |
| Qwen3.5-397B-A17B | 45.16 | 54.91 | 87.43 | 86.50 | 85.12 | 57.06 | 53.33 | 49.51 | 89.57 | 76.00 | 72.67 | 20.36 | 47.50 | 72.17 | 65.55 |
| Model | Incremental Evidence | Dedicated Distractors | Held-in | Fine-grained Perception | Difficult Perception & Reason | Avg. Only Held-out | ||||||||
| ZoomGain Bench | Zoom Bench | V* Bench | HR 4K | HR 8K | MME-RW Lite | Tree Bench | Visual Probe | Baby Vision | Perception Bench | O3- Bench | ||||
| Qwen3.5-4B | – | – | 30.03 | 48.88 | 81.68 | 81.25 | 77.63 | 57.89 | 49.38 | 43.30 | 14.69 | 33.10 | 54.20 | 54.20 |
| +ZoomGain 9K | ✗ | ✓ | 49.71 | 56.45 | 88.48 | 85.50 | 81.75 | 60.24 | 48.40 | 52.82 | 18.56 | 34.70 | 58.84 | 58.57 |
| +ZoomGain 9K | ✓ | ✗ | 46.85 | 57.04 | 90.05 | 85.75 | 80.25 | 62.69 | 48.89 | 54.76 | 17.53 | 34.97 | 59.42 | 59.14 |
| +ZoomGain 9K | ✓ | ✓ | 55.81 | 59.88 | 90.05 | 87.25 | 83.88 | 61.59 | 49.14 | 57.28 | 21.13 | 36.23 | 63.19 | 60.96 |
Appendix figures & tables11 assets
Supplementary material from the paper’s appendix.
Appendix
| Model | Roles |
|---|---|
| Qwen3.5-397B-A17B Team (2026) | Initial global scene captioning and paired-view captioning ( ); grounding; crop anchor enumeration; joint crop/full-image audit and rewriting; blind answering; global-view error collection; visual distractor generation; final MCQ verification. |
| GLM-5.2 GLM-5-Team et al. (2026) | Incremental fact extraction and QA generation. |
| Qwen3-VL-235B-A22B-Instruct Bai et al. (2025) | Grounding; crop-based verification; blind answering; global-view error collection; final MCQ verification. |
| Kimi-K2.6 Team et al. (2026b) | Grounding; crop-based verification; blind answering; global-view error collection; final MCQ verification. |
| Qwen3.5-122B-A10B Team (2026) | Answer-equivalence judging. |
| DeepSeek-V4-Pro DeepSeek-AI (2026) | Candidate distractor clustering and option-pool curation. |
Fine-Grained Visual Perception
Fine-grained visual perception studies how models detect, distinguish, and ground subtle visual details, attributes, parts, and changes.
See all 162 papers