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 …

Progressive Contrastive Label Optimization for Source-Free Universal 3D Model Retrieval

J Li, Y Su, D Song, W Li, Y Yang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Unsupervised Cross-Domain 3D Model Retrieval (UCD3DMR) has emerged as an effective
tool for managing 3D model data recently. However, existing UCD3DMR algorithms typically …

Universal domain adaptation for machinery fault diagnosis based on multi‐scale dual attention network and entropy‐based clustering

CY Lee, GL Zhuo - IET Science, Measurement & Technology, 2024 - Wiley Online Library
Recently, data‐driven cross‐domain fault diagnosis methods for rotating machinery have
been successfully developed. However, most existing diagnostic methods assume that the …

Adaptive Prompt Learning with Negative Textual Semantics and Uncertainty Modeling for Universal Multi-Source Domain Adaptation

Y Yang, L Wen, Y Xu, J Zhou, Y Wang - arxiv preprint arxiv:2404.14696, 2024 - arxiv.org
Universal Multi-source Domain Adaptation (UniMDA) transfers knowledge from multiple
labeled source domains to an unlabeled target domain under domain shifts (different data …