Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance …
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 …
Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly …
Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen …
Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled target domain, but it requires to access the source data which often raises concerns in data …
H Xia, H Zhao, Z Ding - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Abstract Unsupervised Domain Adaptation solves knowledge transfer along with the coexistence of well-annotated source domain and unlabeled target instances. However, the …
X Li, M Jiang, X Zhang, M Kamp, Q Dou - arXiv preprint arXiv:2102.07623, 2021 - arxiv.org
The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence …
DP Fan, GP Ji, MM Cheng… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
We present the first systematic study on concealed object detection (COD), which aims to identify objects that are visually embedded in their background. The high intrinsic similarities …
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to a different unlabeled target domain. Most existing UDA methods focus on …