Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Atabuzzaman, Md., Zhang, Andrew, Thomas, Chris
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909825446707200
author Atabuzzaman, Md.
Zhang, Andrew
Thomas, Chris
author_facet Atabuzzaman, Md.
Zhang, Andrew
Thomas, Chris
contents Large Vision-Language Models (LVLMs) have demonstrated impressive performance on vision-language reasoning tasks. However, their potential for zero-shot fine-grained image classification, a challenging task requiring precise differentiation between visually similar categories, remains underexplored. We present a novel method that transforms zero-shot fine-grained image classification into a visual question-answering framework, leveraging LVLMs' comprehensive understanding capabilities rather than relying on direct class name generation. We enhance model performance through a novel attention intervention technique. We also address a key limitation in existing datasets by developing more comprehensive and precise class description benchmarks. We validate the effectiveness of our method through extensive experimentation across multiple fine-grained image classification benchmarks. Our proposed method consistently outperforms the current state-of-the-art (SOTA) approach, demonstrating both the effectiveness of our method and the broader potential of LVLMs for zero-shot fine-grained classification tasks. Code and Datasets: https://github.com/Atabuzzaman/Fine-grained-classification
format Preprint
id arxiv_https___arxiv_org_abs_2510_03903
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models
Atabuzzaman, Md.
Zhang, Andrew
Thomas, Chris
Computer Vision and Pattern Recognition
Large Vision-Language Models (LVLMs) have demonstrated impressive performance on vision-language reasoning tasks. However, their potential for zero-shot fine-grained image classification, a challenging task requiring precise differentiation between visually similar categories, remains underexplored. We present a novel method that transforms zero-shot fine-grained image classification into a visual question-answering framework, leveraging LVLMs' comprehensive understanding capabilities rather than relying on direct class name generation. We enhance model performance through a novel attention intervention technique. We also address a key limitation in existing datasets by developing more comprehensive and precise class description benchmarks. We validate the effectiveness of our method through extensive experimentation across multiple fine-grained image classification benchmarks. Our proposed method consistently outperforms the current state-of-the-art (SOTA) approach, demonstrating both the effectiveness of our method and the broader potential of LVLMs for zero-shot fine-grained classification tasks. Code and Datasets: https://github.com/Atabuzzaman/Fine-grained-classification
title Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.03903