Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks
via randomly masking image patches and reconstruction. However, effective data …

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

Contrastive learning is one of the fastest growing research areas in machine learning due to
its ability to learn useful representations without labeled data. However, contrastive learning …

In this paper, we tackle the problem of learning visual representations from unlabeled scene-
centric data. Existing works have demonstrated the potential of utilizing the underlying …

Masked Image Modeling (MIM) has emerged as a promising method for deriving visual
representations from unlabeled image data by predicting missing pixels from masked …

We argue that a form of the valuable information provided by the auxiliary information is its
implied data clustering information. For instance, considering hashtags as auxiliary …

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

Contrastive self-supervised learning has emerged as a promising approach to unsupervised
visual representation learning. In general, these methods learn global (image-level) …

Pre-training convolutional neural networks with weakly-supervised and self-supervised
strategies is becoming increasingly popular for several computer vision tasks. However, due …

Advanced self-supervised visual representation learning methods rely on the instance
discrimination (ID) pretext task. We point out that the ID task has an implicit semantic …