SimTriplet: Simple Triplet Representation Learning with a Single GPU

TL;DR

SimTriplet introduces a simple triplet-based self-supervised learning method for pathological images that achieves high performance with minimal labeled data using only a single GPU.

Contribution

The paper presents a novel triplet-based learning approach that leverages multi-view medical images without negative samples, enabling effective training on a single GPU.

Findings

Achieved 10.58% better performance than supervised learning.

Outperformed SimSiam by 2.13%.

Performed well with only 1% labeled data.

Abstract

Contrastive learning is a key technique of modern self-supervised learning. The broader accessibility of earlier approaches is hindered by the need of heavy computational resources (e.g., at least 8 GPUs or 32 TPU cores), which accommodate for large-scale negative samples or momentum. The more recent SimSiam approach addresses such key limitations via stop-gradient without momentum encoders. In medical image analysis, multiple instances can be achieved from the same patient or tissue. Inspired by these advances, we propose a simple triplet representation learning (SimTriplet) approach on pathological images. The contribution of the paper is three-fold: (1) The proposed SimTriplet method takes advantage of the multi-view nature of medical images beyond self-augmentation; (2) The method maximizes both intra-sample and inter-sample similarities via triplets from positive pairs, without using negative samples; and (3) The recent mix precision training is employed to advance the training by only using a single GPU with 16GB memory. By learning from 79,000 unlabeled pathological patch images, SimTriplet achieved 10.58% better performance compared with supervised learning. It also achieved 2.13% better performance compared with SimSiam. Our proposed SimTriplet can achieve decent performance using only 1% labeled data. The code and data are available at https://github.com/hrlblab/SimTriple.