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 …

Review the state-of-the-art technologies of semantic segmentation based on deep learning

Y Mo, Y Wu, X Yang, F Liu, Y Liao - Neurocomputing, 2022 - Elsevier
The goal of semantic segmentation is to segment the input image according to semantic
information and predict the semantic category of each pixel from a given label set. With the …

Unisim: A neural closed-loop sensor simulator

Z Yang, Y Chen, J Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Rigorously testing autonomy systems is essential for making safe self-driving vehicles (SDV)
a reality. It requires one to generate safety critical scenarios beyond what can be collected …

MIC: Masked image consistency for context-enhanced domain adaptation

L Hoyer, D Dai, H Wang… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In unsupervised domain adaptation (UDA), a model trained on source data (eg synthetic) is
adapted to target data (eg real-world) without access to target annotation. Most previous …

Continual test-time domain adaptation

Q Wang, O Fink, L Van Gool… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Test-time domain adaptation aims to adapt a source pre-trained model to a target domain
without using any source data. Existing works mainly consider the case where the target …

Test-time training with masked autoencoders

Y Gandelsman, Y Sun, X Chen… - Advances in Neural …, 2022 - proceedings.neurips.cc
Test-time training adapts to a new test distribution on the fly by optimizing a model for each
test input using self-supervision. In this paper, we use masked autoencoders for this one …

Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation

L Hoyer, D Dai, L Van Gool - Proceedings of the IEEE/CVF …, 2022 - openaccess.thecvf.com
As acquiring pixel-wise annotations of real-world images for semantic segmentation is a
costly process, a model can instead be trained with more accessible synthetic data and …

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 …

Exploring visual prompts for adapting large-scale models

H Bahng, A Jahanian, S Sankaranarayanan… - arXiv preprint arXiv …, 2022 - arxiv.org
We investigate the efficacy of visual prompting to adapt large-scale models in vision.
Following the recent approach from prompt tuning and adversarial reprogramming, we learn …

Hrda: Context-aware high-resolution domain-adaptive semantic segmentation

L Hoyer, D Dai, L Van Gool - European conference on computer vision, 2022 - Springer
Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source
domain (eg synthetic data) to the target domain (eg real-world data) without requiring further …