3 papers
cs.CV2025
Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation
Kerun Mi, Guoliang Kang, Guangyu Li +3
Class-Incremental Unsupervised Domain Adaptation (CI-UDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where the sets of potential target class…
cs.CV2025
PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting
Yu Wang, Xiaobao Wei, Ming Lu +1
Previous methods utilize the Neural Radiance Field (NeRF) for panoptic lifting, while their training and rendering speed are unsatisfactory. In contrast, 3D Gaussian Splatting (3DG…
cs.CV2024
SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training
Gengwei Zhang, Liyuan Wang, Guoliang Kang +2
In recent years, continual learning with pre-training (CLPT) has received widespread interest, instead of its traditional focus of training from scratch. The use of strong pre-trai…