In this paper we first assess and harness various Vision Foundation Models (VFMs) in the
context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation …

Camouflaged object detection has attracted a lot of attention in computer vision. The main
challenge lies in the high degree of similarity between camouflaged objects and their …

Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability
to generate creative content, specialize to user data through few-shot fine-tuning, and …

Domain-generalized urban-scene semantic segmentation (USSS) aims to learn generalized
semantic predictions across diverse urban-scene styles. Unlike generic domain gap …

Prototypical contrastive learning (PCL) has been widely used to learn class-wise domain-
invariant features for domain generalization semantic segmentation. These methods …

Currently high-definition (HD) map construction leans towards a lightweight online
generation tendency which aims to preserve timely and reliable road scene information …

Domain generalization (DG) remains a significant challenge for perception based on deep
neural networks (DNN), where domain shifts occur due to lighting, weather, or geolocation …

The rapid development of Vision Foundation Model (VFM) brings inherent out-domain
generalization for a variety of down-stream tasks. Among them, domain generalized …

Vision-Language Models (VLMs), pre-trained on large-scale datasets, have shown
impressive performance in various visual recognition tasks. This advancement paves the …

Learning scene semantics that can be well generalized to foggy conditions is important for
safety-crucial applications such as autonomous driving. Existing methods need both …