Self-supervised representation learning for visual pre-training has achieved remarkable
success with sample (instance or pixel) discrimination and semantics discovery of instance …

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 …

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

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 …

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 …

Contrastive learning methods for unsupervised visual representation learning have reached
remarkable levels of transfer performance. We argue that the power of contrastive learning …

Contrastive self-supervised learning has outperformed supervised pretraining on many
downstream tasks like segmentation and object detection. However, current methods are …

We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …

Self-supervised learning has achieved significant success in learning visual representations
without the need for manual annotation. To obtain generalizable representations, a …

Self-supervised learning (SSL) has delivered superior performance on a variety of
downstream vision tasks. Two main-stream SSL frameworks have been proposed, ie …