Rethinking Transfer Learning for Medical Image Classification

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 t...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Le, Peng, Liang, Hengyue, Luo, Gaoxiang, Li, Taihui, Sun, Ju
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 16.12.2023
Subjects
Artificial neural networks
Classification
Image classification
Learning
Medical imaging
Online AccessGet full text

Cover

More Information
Summary: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. Our code is available at: https://github.com/sun-umn/TTL
ISSN:2331-8422