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 …

In search of lost online test-time adaptation: A survey

Z Wang, Y Luo, L Zheng, Z Chen, S Wang… - International Journal of …, 2024 - Springer
This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing
on effectively adapting machine learning models to distributionally different target data upon …

Recent advances in complementary label learning

Y Tian, H Jiang - Information Fusion, 2024 - Elsevier
Abstract Complementary Label Learning (CLL), a crucial aspect of weakly supervised
learning, has seen significant theoretical and practical advancements. However, a …

Noise-robust continual test-time domain adaptation

Z Yu, J Li, Z Du, F Li, L Zhu, Y Yang - Proceedings of the 31st ACM …, 2023 - dl.acm.org
Continual test-time domain adaptation (TTA) is a challenging topic in the field of source-free
domain adaptation, which focuses on addressing cross-domain multimedia information …

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

Z Chen, J Meng, M Baktashmotlagh, Z Huang… - arXiv preprint arXiv …, 2024 - arxiv.org
LiDAR-based 3D object detection is pivotal across many applications, yet the performance
of such detection systems often degrades after deployment, especially when faced with …

Multi-source fully test-time adaptation

Y Du, S Luo, Y Xin, M Chen, S Feng, M Zhang, C Wang - Neural Networks, 2025 - Elsevier
Deep neural networks have significantly advanced various fields. However, these models
often encounter difficulties in achieving effective generalization when the distribution of test …

Learning with Complementary Labels Revisited: A Consistent Approach via Negative-Unlabeled Learning

W Wang, T Ishida, YJ Zhang, G Niu… - arXiv preprint arXiv …, 2023 - arxiv.org
Complementary-label learning is a weakly supervised learning problem in which each
training example is associated with one or multiple complementary labels indicating the …

DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection

Z Chen, Z Wang, S Wang, Z Huang, Y Luo - arXiv preprint arXiv …, 2024 - arxiv.org
LiDAR-based 3D object detection has seen impressive advances in recent times. However,
deploying trained 3D detectors in the real world often yields unsatisfactory performance …

ESP-Zero: Unsupervised enhancement of zero-shot classification for Extremely Sparse Point cloud

J Han, Z Cao, W Zheng, X Zhou, X He, Y Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
In recent years, zero-shot learning has attracted the focus of many researchers, due to its
flexibility and generality. Many approaches have been proposed to achieve the zero-shot …

A Zero-Shot Domain Adaptation Framework for Computed Tomography Via Reinforcement Learning and Volume Rendering

A Li, Y Zhao, F Bai, J Han… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
The Domain gap is an important issue when applying AI-based approaches to clinical use.
Many recent approaches introduce domain adaptation (DA) to eliminate the influence of the …