已发表成果:
WOK 论文 183 篇;中文核心 7 篇;其它论文 3 篇;专利发明 1 个;
Lottery Jackpots Exist in Pre-Trained Models
CrackF-Net: a pixel-level segmentation network for pavement crack detection
Shadow Removal by High-Quality Shadow Synthesis
AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
A Unified Framework for 3D Point Cloud Visual Grounding
CF-ViT: A General Coarse-to-Fine Method for Vision Transformer
Shadow-Aware Dynamic Convolution for Shadow Removal
Spatial Re-parameterization for N:M Sparsity
DiffRate: Differentiable Compression Rate for Efficient Vision Transformers
MultiQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks
Model compression optimized neural network controller for nonlinear systems
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Bi-directional Masks for Efficient N:M Sparse Training
REAL-TIME IMAGE DEMOIRéING ON MOBILE DEVICES
A Secure and Privacy-Preserving E-Government Framework Using Blockchain and Artificial Immunity
Fuzzy-Rough Intrigued Harmonic Discrepancy Clustering
Training Compact CNNs for Image Classification Using Dynamic-Coded Filter Fusion
Internal Model Control Structure Inspired Robotic Calligraphy System
Automated Action Evaluation for Robotic Imitation Learning via Siamese Neural Networks
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Bi-directional Masks for Efficient N:M Sparse Training
An Action Evaluation and?Scaling Algorithm for?Robot Motion Planning
Meta Architecture for Point Cloud Analysis
Discriminator-Cooperated Feature Map Distillation for GAN Compression
Wavelet transform and deep learning-based obstructive sleep apnea detection from single-lead ECG signals
AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
SMMix: Self-Motivated Image Mixing for Vision Transformers
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers
Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle
REAL-TIME IMAGE DEMOIRéING ON MOBILE DEVICES