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 …

In this paper, we propose an instance similarity learning (ISL) method for unsupervised
feature representation. Conventional methods assign close instance pairs in the feature …

Cluster discrimination is an effective pretext task for unsupervised representation learning,
which often consists of two phases: clustering and discrimination. Clustering is to assign …

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 learning based on instance discrimination has shown remarkable progress.
In particular, contrastive learning, which regards each image as well as its augmentations as …

Unsupervised visual representation learning has gained much attention from the computer
vision community because of the recent achievement of contrastive learning. Most of the …

Recent self-supervised visual representation methods are closing the gap with supervised
learning performance. Most of these successful methods rely on maximizing the similarity …

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

This paper presents parametric instance classification (PIC) for unsupervised visual feature
learning. Unlike the state-of-the-art approaches which do instance discrimination in a dual …

Self-supervised learning algorithms based on instance discrimination effectively prevent
representation collapse and produce promising results in representation learning. However …