Rethinking Transfer Learning for Medical Image Classification
Peng, L.; Liang, H.; Luo, G.; Li, T.; Sun, J.
Show 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. Our code is available at: https://github.com/sun-umn/TTL.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement 97%
- Small hand-designed convolutional neural networks outperform transfer learning in automated cell shape detection in confluent tissues 94%
- Compressive Big Data Analytics: An Ensemble Meta-Algorithm for High-dimensional Multisource Datasets 94%
Similar papers in this journal
- Spatial Transcriptomics Expression Prediction from Histopathology Based on Cross-Modal Mask Reconstruction and Contrastive Learning 94%
- STAMP: Simultaneous Training and Model Pruning for Low Data Regimes in Medical Image Segmentation 94%
- Clinical Validation of Saliency Maps for Understanding Deep Neural Networks in Ophthalmology 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.