1 citations · 1 across the 4 of their papers we have counts for
5 papers
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…
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…
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…
DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation
Guang Yang, Yin Tang, Zhijian Wu +3
Recent mainstream masked distillation methods function by reconstructing selectively masked areas of a student network from the feature map of its teacher counterpart. In these met…
EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detection
Guangtao Wang, Jun Li, Zhijian Wu +3
In recent years, deep convolutional neural networks (CNN) have significantly advanced face detection. In particular, lightweight CNNbased architectures have achieved great success…