Keywords: Self-supervised Learning, Instance Discrimination, Transfer Learning, Contrastive Learning
TL;DR: We propose Context-Aware instance Discrimination (CAiD), a simple yet powerful self-supervised framework that formulates an auxiliary context prediction task to equip instance discrimination learning with context-aware representations.
Abstract: Recently, self-supervised instance discrimination methods have achieved significant success in learning visual representations from unlabeled photographic images. However, given the marked differences between photographic and medical images, the efficacy of instance-based objectives, focusing on learning the most discriminative global features in the image (i.e., wheels in bicycle), remains unknown in medical imaging. Our preliminary analysis showed that high global similarity of medical images in terms of anatomy hampers instance discrimination methods for capturing a set of distinct features, negatively impacting their performance on medical downstream tasks. To alleviate this limitation, we have developed a simple yet effective self-supervised framework, called Context-Aware instance Discrimination (CAiD). CAiD aims to improve instance discrimination learning by providing finer and more discriminative information encoded from a diverse local context of unlabeled medical images. We conduct a systematic analysis to investigate the utility of the learned features from a three-pronged perspective: (i) generalizability and transferability, (ii) separability in the embedding space, and (iii) reusability. Our extensive experiments demonstrate that CAiD (1) enriches representations learned from existing instance discrimination methods; (2) delivers more discriminative features by adequately capturing finer contextual information from individual medial images; and (3) improves reusability of low/mid-level features compared to standard instance discriminative methods. As open science, all codes and pre-trained models are available on our GitHub page: https://github.com/JLiangLab/CAiD.
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: both
Primary Subject Area: Unsupervised Learning and Representation Learning
Secondary Subject Area: Transfer Learning and Domain Adaptation
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.
Code And Data: https://github.com/JLiangLab/CAiD Data: In this study, we used the following four publicly available datasets: (1) CheXpert: https://stanfordmlgroup.github.io/competitions/chexpert/ (2) ChestX-ray14: https://nihcc.app.box.com/v/ChestXray-NIHCC (3) SIIM-ACR Pneumothorax Segmentation: https://www.kaggle.com/c/siim-acr-pneumothorax-segmentation/ (4) Montgomery County X-ray Set: https://lhncbc.nlm.nih.gov/LHC-publications/pubs/TuberculosisChestXrayImageDataSets.html