Evaluating the Robustness of Self-Supervised Learning in Medical Imaging

05/14/2021
by   Fernando Navarro, et al.
16

Self-supervision has demonstrated to be an effective learning strategy when training target tasks on small annotated data-sets. While current research focuses on creating novel pretext tasks to learn meaningful and reusable representations for the target task, these efforts obtain marginal performance gains compared to fully-supervised learning. Meanwhile, little attention has been given to study the robustness of networks trained in a self-supervised manner. In this work, we demonstrate that networks trained via self-supervised learning have superior robustness and generalizability compared to fully-supervised learning in the context of medical imaging. Our experiments on pneumonia detection in X-rays and multi-organ segmentation in CT yield consistent results exposing the hidden benefits of self-supervision for learning robust feature representations.

READ FULL TEXT

page 3

page 8

research
03/29/2021

Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data

Self-supervised learning has enabled significant improvements on natural...
research
06/14/2022

Self-Supervision on Images and Text Reduces Reliance on Visual Shortcut Features

Deep learning models trained in a fully supervised manner have been show...
research
11/25/2021

Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements

Deep networks provide state-of-the-art performance in multiple imaging i...
research
05/19/2022

Free Lunch for Surgical Video Understanding by Distilling Self-Supervisions

Self-supervised learning has witnessed great progress in vision and NLP;...
research
10/14/2022

Data-Limited Tissue Segmentation using Inpainting-Based Self-Supervised Learning

Although supervised learning has enabled high performance for image segm...
research
05/28/2021

About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data Annotations

Self-supervised learning methods for computer vision have demonstrated t...
research
12/04/2020

Rethinking supervised learning: insights from biological learning and from calling it by its name

The renaissance of artificial neural networks was catalysed by the succe...

Please sign up or login with your details

Forgot password? Click here to reset