8 citations · 8 across the 2 of their papers we have counts for
3 papers
cs.CV2021
On-target Adaptation
Dequan Wang, Shaoteng Liu, Sayna Ebrahimi +2
Domain adaptation seeks to mitigate the shift between training on the \emph{source} domain and testing on the \emph{target} domain. Most adaptation methods rely on the source data…
cs.LG2021★ 8 cited
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
Dequan Wang, An Ju, Evan Shelhamer +2
Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should…
cs.LG2021
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Jianfei Chen, Lianmin Zheng, Zhewei Yao +4
The increasing size of neural network models has been critical for improvements in their accuracy, but device memory is not growing at the same rate. This creates fundamental chall…