Saved in:
Bibliographic Details
Main Authors: Marsili, Damiano, Mehta, Aditya, Lin, Ryan Y., Gkioxari, Georgia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.23592
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911420317171712
author Marsili, Damiano
Mehta, Aditya
Lin, Ryan Y.
Gkioxari, Georgia
author_facet Marsili, Damiano
Mehta, Aditya
Lin, Ryan Y.
Gkioxari, Georgia
contents Vision-language models (VLMs) excel at broad visual understanding but remain coarse-grained, exhibit visual biases, and miss subtle visual details. Existing training corpora reinforce this limitation by emphasizing general recognition ("Is it a cat or a dog?") over fine-grained perception. To address this, we introduce a new training corpus and task designed to enhance the perceptual abilities of VLMs. TWIN is a large-scale dataset of 561,000 image-pair queries that task models to determine whether two visually similar images depict the same object, encouraging attention to nuanced visual cues. The dataset spans a diverse range of everyday objects across contexts, viewpoints, and appearances. Fine-tuning VLMs on TWIN yields notable gains in fine-grained recognition, even on unseen domains such as art, animals, plants, and landmarks. To quantify these gains, we introduce FGVQA, a benchmark suite of 12,000 queries that repurposes fine-grained recognition and retrieval datasets from multiple domains. While existing VLMs struggle on FGVQA, when fine-tuned on TWIN they improve by up to 19.3%, without compromising performance on general VQA benchmarks. Finally, our TWIN dataset scales favorably with object annotations, and our analysis shows that scale is key to performance. We envision TWIN as a drop-in addition to open-source VLM training corpora, advancing perceptual precision of future models. Project webpage: https://glab-caltech.github.io/twin/
format Preprint
id arxiv_https___arxiv_org_abs_2512_23592
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Same or Not? Enhancing Visual Perception in Vision-Language Models
Marsili, Damiano
Mehta, Aditya
Lin, Ryan Y.
Gkioxari, Georgia
Computer Vision and Pattern Recognition
Vision-language models (VLMs) excel at broad visual understanding but remain coarse-grained, exhibit visual biases, and miss subtle visual details. Existing training corpora reinforce this limitation by emphasizing general recognition ("Is it a cat or a dog?") over fine-grained perception. To address this, we introduce a new training corpus and task designed to enhance the perceptual abilities of VLMs. TWIN is a large-scale dataset of 561,000 image-pair queries that task models to determine whether two visually similar images depict the same object, encouraging attention to nuanced visual cues. The dataset spans a diverse range of everyday objects across contexts, viewpoints, and appearances. Fine-tuning VLMs on TWIN yields notable gains in fine-grained recognition, even on unseen domains such as art, animals, plants, and landmarks. To quantify these gains, we introduce FGVQA, a benchmark suite of 12,000 queries that repurposes fine-grained recognition and retrieval datasets from multiple domains. While existing VLMs struggle on FGVQA, when fine-tuned on TWIN they improve by up to 19.3%, without compromising performance on general VQA benchmarks. Finally, our TWIN dataset scales favorably with object annotations, and our analysis shows that scale is key to performance. We envision TWIN as a drop-in addition to open-source VLM training corpora, advancing perceptual precision of future models. Project webpage: https://glab-caltech.github.io/twin/
title Same or Not? Enhancing Visual Perception in Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.23592