Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation
Year: 2025
Type: preprint
Abstract: Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception capabilities, garnering significant attention. While numerous evaluation studies have emerged, assessing LVLMs both holistically and on specialized tasks, fine-grained image tasks-fundamental to computer vision-remain largely unexplored. To fill this gap, we introduce a comprehensive fine-grained evaluation benchmark, i.e., FG-BMK, comprising 1.01 million questions and 0.33 million images. Our evaluation systematically examines LVLMs from both human-oriented and machine-oriented perspectives, focusing on their semantic recognition and fine-grained feature representation capabilities. Through extensive experiments on twelve representative LVLMs/VLMs, we uncover key findings regarding the influence of training paradigms, modality alignment, perturbation susceptibility, and fine-grained category reasoning on task performance. This work provides critical insights into the limitations of current LVLMs and offers guidance for future data construction and model design in the development of more advanced LVLMs. Our code is open-source and available at https://github.com/SEU-VIPGroup/FG-BMK.
Source: arXiv (Cornell University)
Authors: Yu, Hong-Tao, Peng, Yuxin, Belongie, Serge, Wei, Xiu-Shen
Institutions: Southeast University, Peking University, University of Copenhagen
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6929316993
Cites:
Cited by:
Related to: