3 papers
cs.CV2026
CoDe-SSM: Context-Detail Decoupled State Space Model for Efficient UHD Image Restoration
Jiaxu Su, Zhijian Wu, Jun Li +2
Ultra-high-definition (UHD) image restoration must balance the aggregation of spatially recurring degradation cues with the preservation of localized image structures. Compact aggr…
cs.CV2026
DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer
Zhengxu He, Jun Li, Zhijian Wu
Large-scale Vision-Language Models (VLMs) encode rich multimodal semantics that are highly beneficial for fine-grained visual categorization (FGVC). However, their prohibitive comp…
cs.CV2024
DFMSD: Dual Feature Masking Stage-wise Knowledge Distillation for Object Detection
Zhourui Zhang, Jun Li, Zhijian Wu +2
In recent years, current mainstream feature masking distillation methods mainly function by reconstructing selectively masked regions of a student network from the feature maps of…