4 citations · 10 across the 9 of their papers we have counts for
11 papers
Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation
Cody Blakeney, Jessica Zosa Forde, Jonathan Frankle +2
Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning prac…
Lipschitz Continuity Retained Binary Neural Network
Yuzhang Shang, Dan Xu, Bin Duan +3
Relying on the premise that the performance of a binary neural network can be largely restored with eliminated quantization error between full-precision weight vectors and their co…
Network Binarization via Contrastive Learning
Yuzhang Shang, Dan Xu, Ziliang Zong +2
Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit. However, there is still a huge performance gap between Binary Neural Net…
Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning
Yuzhang Shang, Bin Duan, Ziliang Zong +2
With the remarkable success of deep learning recently, efficient network compression algorithms are urgently demanded for releasing the potential computational power of edge device…
Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Neural Networks
Cody Blakeney, Gentry Atkinson, Nathaniel Huish +3
Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discriminatio…
Lipschitz Continuity Guided Knowledge Distillation
Yuzhang Shang, Bin Duan, Ziliang Zong +2
Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although grea…