Recent self-supervised representation learning techniques have largely closed the gap
between supervised and unsupervised learning on ImageNet classification. While the …

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training
on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, ie …

This paper is concerned with self-supervised learning for small models. The problem is
motivated by our empirical studies that while the widely used contrastive self-supervised …

Siamese networks have become a common structure in various recent models for
unsupervised visual representation learning. These models maximize the similarity between …

A successful paradigm in representation learning is to perform self-supervised pretraining
using tasks based on mini-batch statistics (eg, SimCLR, VICReg, SwAV, MSN). We show …

Unsupervised visual representation learning remains a largely unsolved problem in
computer vision research. Among a big body of recently proposed approaches for …

In the past few years, we have witnessed remarkable breakthroughs in self-supervised
representation learning. Despite the success and adoption of representations learned …

Unsupervised representation learning with contrastive learning achieves great success
recently. However, these methods have to duplicate each training batch to construct …

Self-supervised learning aims to learn representations from the data itself without explicit
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …

This paper presents SimCLR: a simple framework for contrastive learning of visual
representations. We simplify recently proposed contrastive self-supervised learning …