Rethinking Transfer Learning for Medical Image Classification
Le Peng (University of Minnesota),* Hengyue Liang (University of Minnesota), Gaoxiang Luo (University of Minnesota), Taihui Li (University of Minnesota), Ju Sun (University of Minnesota)
The 34th British Machine Vision Conference
Abstract
Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-dependent, and uniformly finetuning all layers of pretrained models may be suboptimal. This insight has partly motivated the recent differential TL strategies, such as TransFusion (TF) and layer-wise finetuning (LWFT), which treat the layers in the pretrained models differentially. In this paper, we add one more strategy into this family, called TruncatedTL, which reuses and finetunes appropriate bottom layers and directly discards the remaining layers. This yields not only superior MIC performance but also compact models for efficient inference, compared to other differential TL methods.Citation
@inproceedings{Peng_2023_BMVC,
author = {Le Peng and Hengyue Liang and Gaoxiang Luo and Taihui Li and Ju Sun},
title = {Rethinking Transfer Learning for Medical Image Classification},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://bmvc2022.mpi-inf.mpg.de/BMVC2023/0881.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by