Similar to humans' cognitive ability to generalize knowledge and skills, self-supervised
learning (SSL) targets discovering general representations from large-scale data. This …

In this paper, we question if self-supervised learning provides new properties to Vision
Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the …

Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large
computer vision benchmarks. A successful approach to SSL is to learn embeddings which …

Most recent self-supervised methods for learning image representations focus on either
producing a global feature with invariance properties, or producing a set of local features …

We present a large-scale study on unsupervised spatiotemporal representation learning
from videos. With a unified perspective on four recent image-based frameworks, we study a …

Most of the current self-supervised representation learning (SSL) methods are based on the
contrastive loss and the instance-discrimination task, where augmented versions of the …

In self-supervised representation learning, a common idea behind most of the state-of-the-
art approaches is to enforce the robustness of the representations to predefined …

Most successful self-supervised learning methods are trained to align the representations of
two independent views from the data. State-of-the-art methods in video are inspired by …

While deep learning strategies achieve outstanding results in computer vision tasks, one
issue remains: The current strategies rely heavily on a huge amount of labeled data. In many …

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear
what characteristics of their representations lead to high downstream accuracies. In this …