A comprehensive survey on test-time adaptation under distribution shifts

J Liang, R He, T Tan - International Journal of Computer Vision, 2024 - Springer
Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends

J Gui, T Chen, J Zhang, Q Cao, Z Sun… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Contrastive test-time adaptation

D Chen, D Wang, T Darrell… - Proceedings of the …, 2022 - openaccess.thecvf.com
Test-time adaptation is a special setting of unsupervised domain adaptation where a trained
model on the source domain has to adapt to the target domain without accessing source …

Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation

P Zhang, B Zhang, T Zhang, D Chen… - Proceedings of the …, 2021 - openaccess.thecvf.com
Self-training is a competitive approach in domain adaptive segmentation, which trains the
network with the pseudo labels on the target domain. However inevitably, the pseudo labels …

Vicreg: Variance-invariance-covariance regularization for self-supervised learning

A Bardes, J Ponce, Y LeCun - arXiv preprint arXiv:2105.04906, 2021 - arxiv.org
Recent self-supervised methods for image representation learning are based on maximizing
the agreement between embedding vectors from different views of the same image. A trivial …

Generalized source-free domain adaptation

S Yang, Y Wang, J Van De Weijer… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Domain adaptation (DA) aims to transfer the knowledge learned from source
domain to an unlabeled target domain. Some recent works tackle source-free domain …

Attracting and dispersing: A simple approach for source-free domain adaptation

S Yang, S Jui, J van de Weijer - Advances in Neural …, 2022 - proceedings.neurips.cc
We propose a simple but effective source-free domain adaptation (SFDA) method. Treating
SFDA as an unsupervised clustering problem and following the intuition that local neighbors …

Source-free domain adaptation via distribution estimation

N Ding, Y Xu, Y Tang, C Xu… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract Domain Adaptation aims to transfer the knowledge learned from a labeled source
domain to an unlabeled target domain whose data distributions are different. However, the …

Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer

J Liang, D Hu, Y Wang, R He… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but
different well-labeled source domain to a new unlabeled target domain. Most existing UDA …

Semi-supervised and unsupervised deep visual learning: A survey

Y Chen, M Mancini, X Zhu… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
State-of-the-art deep learning models are often trained with a large amount of costly labeled
training data. However, requiring exhaustive manual annotations may degrade the model's …