The booming of 3D recognition in the 2020s began with the introduction of point cloud
transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models …

This study addresses the Domain-Class Incremental Learning problem, a realistic but
challenging continual learning scenario where both the domain distribution and target …

Abstract This paper introduces Unified Language-driven Zero-shot Domain Adaptation
(ULDA) a novel task setting that enables a single model to adapt to diverse target domains …

Machine learning algorithms have achieved remarkable success across various disciplines,
use cases and applications, under the prevailing assumption that training and test samples …

Deep learning has achieved impressive results in nuclei segmentation, but the massive
requirement for pixel-wise labels remains a significant challenge. To alleviate the annotation …

In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-
Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's …

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test
data with potential distribution shifts. Most existing TTA methods focus on classification …

Recently, remote sensing images (RSIs) domain adaptation segmentation has been
extensively studied. However, existing methods generally assume that source RSIs must be …

Real-world application models are commonly deployed in dynamic environments, where the
target domain distribution undergoes temporal changes. Continual Test-Time Adaptation …

Online Domain Adaptation (OnDA) is designed to handle unforeseeable domain changes at
minimal cost that occur during the deployment of the model, lacking clear boundaries …