Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different …
J Li, Z Yu, Z Du, L Zhu, HT Shen - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
Over the past decade, domain adaptation has become a widely studied branch of transfer learning which aims to improve performance on target domains by leveraging knowledge …
S Choi, S Yang, S Choi, S Yun - European Conference on Computer …, 2022 - Springer
This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data from the target domain to alleviate …
Z Wu, DP Paudel, DP Fan, J Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Depth cues are known to be useful for visual perception. However, direct measurement of depth is often impracticable. Fortunately, though, modern learning-based methods offer …
Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the …
Y Liu, W Zhang, J Wang, J Wang - arXiv preprint arXiv:2112.15278, 2021 - arxiv.org
In the last decade, many deep learning models have been well trained and made a great success in various fields of machine intelligence, especially for computer vision and natural …
Q Chu, S Li, G Chen, K Li, X Li - … of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Source-free object detection (SFOD) aims to transfer a detector pre-trained on a label-rich source domain to an unlabeled target domain without seeing source data. While most …
K Li, J Lu, H Zuo, G Zhang - IEEE Transactions on Fuzzy …, 2023 - ieeexplore.ieee.org
Unsupervised domain adaptation deals with a task from an unlabeled target domain by leveraging the knowledge gained from labeled source domain (s). The fuzzy system is …
Cost-effective depth and infrared sensors as alternatives to usual RGB sensors are now a reality, and have some advantages over RGB in domains like autonomous navigation and …