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

Abstract Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for
computer vision tasks, while the self-attention computation in Transformer scales …

In this paper, we propose a recurrent framework for joint unsupervised learning of deep
representations and image clusters. In our framework, successive operations in a clustering …

Masked image modelling (eg, Masked AutoEncoder) and contrastive learning (eg,
Momentum Contrast) have shown impressive performance on unsupervised visual …

We investigate a fundamental aspect of machine vision: the measurement of features by
revisiting clustering one of the most classic approaches in machine learning and data …

Representation learning promises to unlock deep learning for the long tail of vision tasks
without expensive labelled datasets. Yet, the absence of a unified evaluation for general …

In contrastive self-supervised learning, the common way to learn discriminative
representation is to pull different augmented" views" of the same image closer while pushing …

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

With the remarkable progress of deep neural networks in computer vision, data mixing
augmentation techniques are widely studied to alleviate problems of degraded …

Over the last years, deep convolutional neural networks (ConvNets) have transformed the
field of computer vision thanks to their unparalleled capacity to learn high level semantic …