Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations
arXiv:2007.07423
Abstract
In deep learning era, pretrained models play an important role in medical image analysis, in which ImageNet pretraining has been widely adopted as the best way. However, it is undeniable that there exists an obvious domain gap between natural images and medical images. To bridge this gap, we propose a new pretraining method which learns from 700k radiographs given no manual annotations. We call our method as Comparing to Learn (C2L) because it learns robust features by comparing different image representations. To verify the effectiveness of C2L, we conduct comprehensive ablation studies and evaluate it on different tasks and datasets. The experimental results on radiographs show that C2L can outperform ImageNet pretraining and previous state-of-the-art approaches significantly. Code and models are available.
arXiv commentMICCAI 2020 early accept; Code and pretrained models available at http://github.com/funnyzhou/C2L_MICCAI2020
References in corpus (5)
- mixup: Beyond Empirical Risk Minimization
- Improved Regularization of Convolutional Neural Networks with Cutout
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Momentum Contrast for Unsupervised Visual Representation Learning
- MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs