Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised …
J Wu, J Hobbs, N Hovakimyan - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Contrastive learning models based on Siamese structure have demonstrated remarkable performance in self-supervised learning. Such a success of contrastive learning relies on …
Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs …
S Kim, G Lee, S Bae, SY Yun - arXiv preprint arXiv:2010.06300, 2020 - researchgate.net
Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation. By learning to contrast positive pairs' representation from the …
Y Zhang, X Zhang, J Li, RC Qiu, H Xu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive …
Z Jiang, T Chen, T Chen… - Advances in neural …, 2021 - proceedings.neurips.cc
Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes. That implies a tantalizing possibility of …
Z Xie, Y Lin, Z Zhang, Y Cao… - Proceedings of the …, 2021 - openaccess.thecvf.com
Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning …
G Wang, K Wang, G Wang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Self-supervised learning (especially contrastive learning) has attracted great interest due to its huge potential in learning discriminative representations in an unsupervised manner …
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These …