2 papers
cs.CV2023
DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing
Songling Zhu, Ronghua Shang, Bo Yuan +3
The knowledge distillation uses a high-performance teacher network to guide the student network. However, the performance gap between the teacher and student networks can affect th…
cs.LG2023
A Multi-objective Complex Network Pruning Framework Based on Divide-and-conquer and Global Performance Impairment Ranking
Ronghua Shang, Songling Zhu, Yinan Wu +3
Model compression plays a vital role in the practical deployment of deep neural networks (DNNs), and evolutionary multi-objective (EMO) pruning is an essential tool in balancing th…