Contrastive Learning Meets Transfer Learning: A Case Study In Medical Image Analysis

03/04/2021
by   Yuzhe Lu, et al.
0

Annotated medical images are typically rarer than labeled natural images since they are limited by domain knowledge and privacy constraints. Recent advances in transfer and contrastive learning have provided effective solutions to tackle such issues from different perspectives. The state-of-the-art transfer learning (e.g., Big Transfer (BiT)) and contrastive learning (e.g., Simple Siamese Contrastive Learning (SimSiam)) approaches have been investigated independently, without considering the complementary nature of such techniques. It would be appealing to accelerate contrastive learning with transfer learning, given that slow convergence speed is a critical limitation of modern contrastive learning approaches. In this paper, we investigate the feasibility of aligning BiT with SimSiam. From empirical analyses, different normalization techniques (Group Norm in BiT vs. Batch Norm in SimSiam) are the key hurdle of adapting BiT to SimSiam. When combining BiT with SimSiam, we evaluated the performance of using BiT, SimSiam, and BiT+SimSiam on CIFAR-10 and HAM10000 datasets. The results suggest that the BiT models accelerate the convergence speed of SimSiam. When used together, the model gives superior performance over both of its counterparts. We hope this study will motivate researchers to revisit the task of aggregating big pre-trained models with contrastive learning models for image analysis.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/26/2022

Parotid Gland MR Image Segmentation Based on Contrastive Learning

Compared with natural images, medical images are difficult to acquire an...
research
04/01/2019

Med3D: Transfer Learning for 3D Medical Image Analysis

The performance on deep learning is significantly affected by volume of ...
research
02/08/2023

Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation

Given the prevalence of 3D medical imaging technologies such as MRI and ...
research
01/25/2019

Surrogate Supervision for Medical Image Analysis: Effective Deep Learning From Limited Quantities of Labeled Data

We investigate the effectiveness of a simple solution to the common prob...
research
03/09/2023

An Evaluation of Non-Contrastive Self-Supervised Learning for Federated Medical Image Analysis

Privacy and annotation bottlenecks are two major issues that profoundly ...
research
04/24/2020

How Much Off-The-Shelf Knowledge Is Transferable From Natural Images To Pathology Images?

Deep learning has achieved a great success in natural image classificati...

Please sign up or login with your details

Forgot password? Click here to reset