To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

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 …

Abstract Unsupervised Domain Adaptation solves knowledge transfer along with the
coexistence of well-annotated source domain and unlabeled target instances. However, the …

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 …

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 …