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

Self-supervised learning algorithms based on instance discrimination train encoders to be
invariant to pre-defined transformations of the same instance. While most methods treat …

Self-supervised representation learning approaches have recently surpassed their
supervised learning counterparts on downstream tasks like object detection and image …

It is useful to automatically compare images based on their visual properties---to predict
which image is brighter, more feminine, more blurry, etc. However, comparative models are …

One desired capability for machines is the ability to transfer their understanding of one
domain to another domain where data is (usually) scarce. Despite ample adaptation of …

Unsupervised image representations have significantly reduced the gap with supervised
pretraining, notably with the recent achievements of contrastive learning methods. These …

Contrastive learning models based on Siamese structure have demonstrated remarkable
performance in self-supervised learning. Such a success of contrastive learning relies on …

The superiority of deeply learned representations relies on large-scale labeled datasets.
However, annotating data are usually expensive or even infeasible in some scenarios. To …

A simple approach to learning invariances in image clas-sification consists in augmenting
the training set with transformed versions of the original images. However, given a large set …

Recently, contrastive learning has largely advanced the progress of unsupervised visual
representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported …