Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Yunqi, An, Sohyun, Bai, Andrew, Lin, Neil Y. C., Hsieh, Cho-Jui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908677338824704
author Hong, Yunqi
An, Sohyun
Bai, Andrew
Lin, Neil Y. C.
Hsieh, Cho-Jui
author_facet Hong, Yunqi
An, Sohyun
Bai, Andrew
Lin, Neil Y. C.
Hsieh, Cho-Jui
contents Despite Multimodal Large Language Models (MLLMs) showing promising results on general zero-shot image classification tasks, fine-grained image classification remains challenging. It demands precise attention to subtle visual details to distinguish between visually similar subcategories--details that MLLMs may easily overlook without explicit guidance. To address this, we introduce AutoSEP, an iterative self-supervised prompt learning framework designed to enhance MLLM fine-grained classification capabilities in a fully unsupervised manner. Our core idea is to leverage unlabeled data to learn a description prompt that guides MLLMs in identifying crucial discriminative features within an image, and boosts classification accuracy. We developed an automatic self-enhancing prompt learning framework called AutoSEP to iteratively improve the description prompt using unlabeled data, based on instance-level classification scoring function. AutoSEP only requires black-box access to MLLMs, eliminating the need for any training or fine-tuning. We evaluate our approach on multiple fine-grained classification datasets. It consistently outperforms other unsupervised baselines, demonstrating the effectiveness of our self-supervised optimization framework. Notably, AutoSEP on average improves 13 percent over standard zero-shot classification and 5 percent over the best-performing baselines. Code is available at: https://github.com/yq-hong/AutoSEP
format Preprint
id arxiv_https___arxiv_org_abs_2506_03195
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs
Hong, Yunqi
An, Sohyun
Bai, Andrew
Lin, Neil Y. C.
Hsieh, Cho-Jui
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Despite Multimodal Large Language Models (MLLMs) showing promising results on general zero-shot image classification tasks, fine-grained image classification remains challenging. It demands precise attention to subtle visual details to distinguish between visually similar subcategories--details that MLLMs may easily overlook without explicit guidance. To address this, we introduce AutoSEP, an iterative self-supervised prompt learning framework designed to enhance MLLM fine-grained classification capabilities in a fully unsupervised manner. Our core idea is to leverage unlabeled data to learn a description prompt that guides MLLMs in identifying crucial discriminative features within an image, and boosts classification accuracy. We developed an automatic self-enhancing prompt learning framework called AutoSEP to iteratively improve the description prompt using unlabeled data, based on instance-level classification scoring function. AutoSEP only requires black-box access to MLLMs, eliminating the need for any training or fine-tuning. We evaluate our approach on multiple fine-grained classification datasets. It consistently outperforms other unsupervised baselines, demonstrating the effectiveness of our self-supervised optimization framework. Notably, AutoSEP on average improves 13 percent over standard zero-shot classification and 5 percent over the best-performing baselines. Code is available at: https://github.com/yq-hong/AutoSEP
title Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.03195