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 …

Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts
between training and testing phases without additional data acquisition or labeling cost; only …

Unsupervised domain adaptation (DA) has gained substantial interest in semantic
segmentation. However, almost all prior arts assume concurrent access to both labeled …

A classifier trained on a dataset seldom works on other datasets obtained under different
conditions due to domain shift. This problem is commonly addressed by domain adaptation …

Test-time adaptation methods have been gaining attention recently as a practical solution for
addressing source-to-target domain gaps by gradually updating the model without requiring …

Current deep visual recognition systems suffer from severe performance degradation when
they encounter new images from classes and scenarios unseen during training. Hence, the …

Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-
by-batch manner during inference. While label distributions often exhibit imbalances in real …

Self-supervised VO methods have shown great success in jointly estimating camera pose
and depth from videos. However, like most data-driven methods, existing VO networks suffer …

Abstract 3D point cloud semantic segmentation is fundamental for autonomous driving. Most
approaches in the literature neglect an important aspect, ie, how to deal with domain shift …