One of the ultimate goals of representation learning is to achieve compactness within a class
and well-separability between classes. Many outstanding metric-based and prototype-based …

Deep neural networks (DNNs) have proven their capabilities in the past years and play a
significant role in environment perception for the challenging application of automated …

In unsupervised domain adaptation (UDA) of remote sensing images (RSIs), the huge
interdomain discrepancies and intradomain variances lead to complicated class-level …

Source-free domain adaptive semantic segmentation has gained increasing attention
recently. It eases the requirement of full data access to the source domain by transferring …

Unsupervised domain adaption has been widely adopted in tasks with scarce annotated
data. Unfortunately, mapping the target-domain distribution to the source-domain …

Multi-source domain adaptation (MSDA) aims to transfer knowledge from multiple source
domains to one target domain. Although multi-source domains contain more complementary …

Few-shot semantic segmentation (FSS) aims to segment unseen objects in a query image
using a few pixel-wise annotated support images, thus expanding the capabilities of …

Video semantic segmentation is beneficial for dynamic scene processing in real-world
environments, and achieves superior performance on independent and identically …

Deep models have demonstrated outstanding ability in various computer vision tasks but are
also notoriously known to generalize poorly when encountering unseen domains with …

While significant progress has been achieved in the field of image semantic segmentation,
the majority of research has been primarily concentrated on daytime scenes. Semantic …