3 papers
cs.CV2026
Degradation-Aware Metric Prompting for Hyperspectral Image Restoration
Binfeng Wang, Di Wang, Haonan Guo +2
Unified hyperspectral image (HSI) restoration aims to recover diverse degradations within a single model. However, current methods often rely on impractical explicit priors or opaq…
cs.CV2026
Supervise-assisted Multi-modality Fusion Diffusion Model for PET Restoration
Yingkai Zhang, Shuang Chen, Ye Tian +3
Positron emission tomography (PET) offers powerful functional imaging but involves radiation exposure. Efforts to reduce this exposure by lowering the radiotracer dose or scan time…
cs.CV2025
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
Peihua Deng, Jiehua Zhang, Xichun Sheng +4
This paper explores the Class-Incremental Source-Free Unsupervised Domain Adaptation (CI-SFUDA) problem, where the unlabeled target data come incrementally without access to labele…