Xu Cheng

15

Papers

44

Total Citations

Papers (15)

SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures

Domain Shifting: A Generalized Solution for Heterogeneous Cross-Modality Person Re-Identification

Can Students Beyond the Teacher? Distilling Knowledge from Teacher’s Bias

From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures

Explaining Knowledge Distillation by Quantifying the Knowledge

TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition

Modality Unifying Network for Visible-Infrared Person Re-Identification

Differentiable Auxiliary Learning for Sketch Re-identification

A Unified Interpretation of Training-Time Out-of-Distribution Detection

FusionPhys: A Flexible Framework for Fusing Complementary Sensing Modalities in Remote Physiological Measurement

Clarifying the Behavior and the Difficulty of Adversarial Training

Layerwise Change of Knowledge in Neural Networks

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities