CVMar 9, 2021

SimTriplet: Simple Triplet Representation Learning with a Single GPU

arXiv:2103.05585v139 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses computational accessibility for medical image analysis, offering an incremental improvement over existing self-supervised methods by reducing hardware needs while maintaining competitive performance.

The paper tackled the problem of high computational resource requirements in contrastive learning for self-supervised representation learning by proposing SimTriplet, a method that uses triplets from multi-view medical images without negative samples and runs on a single GPU, achieving 10.58% better performance than supervised learning and 2.13% better than SimSiam on pathological images.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes