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 …
A Ermolov, A Siarohin, E Sangineto… - … on machine learning, 2021 - proceedings.mlr.press
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 …