8 citations · 13 across the 11 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CV2022
TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks
Taoyong Cui, Jianze Li, Yuhan Dong +1
The orthogonality constraints, including the hard and soft ones, have been used to normalize the weight matrices of Deep Neural Network (DNN) models, especially the Convolutional N…
cs.LG2022★ 5 cited
Data-free Backdoor Removal based on Channel Lipschitzness
Runkai Zheng, Rongjun Tang, Jianze Li +1
Recent studies have shown that Deep Neural Networks (DNNs) are vulnerable to the backdoor attacks, which leads to malicious behaviors of DNNs when specific triggers are attached to…