Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, ie …
This paper is concerned with self-supervised learning for small models. The problem is motivated by our empirical studies that while the widely used contrastive self-supervised …
X Chen, K He - Proceedings of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between …
A successful paradigm in representation learning is to perform self-supervised pretraining using tasks based on mini-batch statistics (eg, SimCLR, VICReg, SwAV, MSN). We show …
Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for …
K Kotar, G Ilharco, L Schmidt… - Proceedings of the …, 2021 - openaccess.thecvf.com
In the past few years, we have witnessed remarkable breakthroughs in self-supervised representation learning. Despite the success and adoption of representations learned …
P Chen, S Liu, J Jia - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Unsupervised representation learning with contrastive learning achieves great success recently. However, these methods have to duplicate each training batch to construct …
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 …
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning …