Saved in:
Bibliographic Details
Main Authors: Li, Sirui, Lin, Li, Huang, Yijin, Cheng, Pujin, Tang, Xiaoying
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.14770
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913481781936128
author Li, Sirui
Lin, Li
Huang, Yijin
Cheng, Pujin
Tang, Xiaoying
author_facet Li, Sirui
Lin, Li
Huang, Yijin
Cheng, Pujin
Tang, Xiaoying
contents In medical contexts, the imbalanced data distribution in long-tailed datasets, due to scarce labels for rare diseases, greatly impairs the diagnostic accuracy of deep learning models. Recent multimodal text-image supervised foundation models offer new solutions to data scarcity through effective representation learning. However, their limited medical-specific pretraining hinders their performance in medical image classification relative to natural images. To address this issue, we propose a novel Text-guided Foundation model Adaptation for Long-Tailed medical image classification (TFA-LT). We adopt a two-stage training strategy, integrating representations from the foundation model using just two linear adapters and a single ensembler for balanced outcomes. Experimental results on two long-tailed medical image datasets validate the simplicity, lightweight and efficiency of our approach: requiring only 6.1% GPU memory usage of the current best-performing algorithm, our method achieves an accuracy improvement of up to 27.1%, highlighting the substantial potential of foundation model adaptation in this area.
format Preprint
id arxiv_https___arxiv_org_abs_2408_14770
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text-guided Foundation Model Adaptation for Long-Tailed Medical Image Classification
Li, Sirui
Lin, Li
Huang, Yijin
Cheng, Pujin
Tang, Xiaoying
Computer Vision and Pattern Recognition
In medical contexts, the imbalanced data distribution in long-tailed datasets, due to scarce labels for rare diseases, greatly impairs the diagnostic accuracy of deep learning models. Recent multimodal text-image supervised foundation models offer new solutions to data scarcity through effective representation learning. However, their limited medical-specific pretraining hinders their performance in medical image classification relative to natural images. To address this issue, we propose a novel Text-guided Foundation model Adaptation for Long-Tailed medical image classification (TFA-LT). We adopt a two-stage training strategy, integrating representations from the foundation model using just two linear adapters and a single ensembler for balanced outcomes. Experimental results on two long-tailed medical image datasets validate the simplicity, lightweight and efficiency of our approach: requiring only 6.1% GPU memory usage of the current best-performing algorithm, our method achieves an accuracy improvement of up to 27.1%, highlighting the substantial potential of foundation model adaptation in this area.
title Text-guided Foundation Model Adaptation for Long-Tailed Medical Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.14770