ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision
Read the original on arXiv AI →ZoomGain introduces a data construction pipeline that exploits the global-to-zoom perception gap to generate fine‑grained visual questions. By creating questions from full‑image context and verifying answers only on zoomed‑in views, the method ensures unambiguous, language‑prior‑free queries and high‑quality distractors for multiple‑choice tasks. Using this pipeline, the authors built ZoomGainBench, a 1,000‑question bilingual benchmark, and demonstrated that training on 9 K ZoomGain samples markedly boosts the visual perception abilities of 4B/9B VLMs, surpassing many larger models on perception benchmarks.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.