How well do self-supervised models transfer?
L Ericsson, H Gouk… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Self-supervised visual representation learning has seen huge progress recently, but no
large scale evaluation has compared the many models now available. We evaluate the …
large scale evaluation has compared the many models now available. We evaluate the …
A broad study on the transferability of visual representations with contrastive learning
Tremendous progress has been made in visual representation learning, notably with the
recent success of self-supervised contrastive learning methods. Supervised contrastive …
recent success of self-supervised contrastive learning methods. Supervised contrastive …
Sit: Self-supervised vision transformer
Self-supervised learning methods are gaining increasing traction in computer vision due to
their recent success in reducing the gap with supervised learning. In natural language …
their recent success in reducing the gap with supervised learning. In natural language …
Self-supervised pretraining of visual features in the wild
Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have
reduced the gap with supervised methods. These results have been achieved in a control …
reduced the gap with supervised methods. These results have been achieved in a control …
When does contrastive visual representation learning work?
Recent self-supervised representation learning techniques have largely closed the gap
between supervised and unsupervised learning on ImageNet classification. While the …
between supervised and unsupervised learning on ImageNet classification. While the …
Revisiting weakly supervised pre-training of visual perception models
Abstract Model pre-training is a cornerstone of modern visual recognition systems. Although
fully supervised pre-training on datasets like ImageNet is still the de-facto standard, recent …
fully supervised pre-training on datasets like ImageNet is still the de-facto standard, recent …
Leverage your local and global representations: A new self-supervised learning strategy
Self-supervised learning (SSL) methods aim to learn view-invariant representations by
maximizing the similarity between the features extracted from different crops of the same …
maximizing the similarity between the features extracted from different crops of the same …
Masked siamese networks for label-efficient learning
Abstract We propose Masked Siamese Networks (MSN), a self-supervised learning
framework for learning image representations. Our approach matches the representation of …
framework for learning image representations. Our approach matches the representation of …
Slip: Self-supervision meets language-image pre-training
Recent work has shown that self-supervised pre-training leads to improvements over
supervised learning on challenging visual recognition tasks. CLIP, an exciting new …
supervised learning on challenging visual recognition tasks. CLIP, an exciting new …
Distilling self-supervised vision transformers for weakly-supervised few-shot classification & segmentation
We address the task of weakly-supervised few-shot image classification and segmentation,
by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed …
by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed …