27 citations · 40 across the 13 of their papers we have counts for
4 papers · 1 filter
Class-aware Information for Logit-based Knowledge Distillation
Shuoxi Zhang, Hanpeng Liu, John E. Hopcroft +1
Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown…
Boosting Adversarial Transferability through Enhanced Momentum
Xiaosen Wang, Jiadong Lin, Han Hu +2
Deep learning models are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations on benign images. Many existing adversarial attack metho…
The Local Dimension of Deep Manifold
Mengxiao Zhang, Wangquan Wu, Yanren Zhang +4
Based on our observation that there exists a dramatic drop for the singular values of the fully connected layers or a single feature map of the convolutional layer, and that the di…
A Powerful Generative Model Using Random Weights for the Deep Image Representation
Kun He, Yan Wang, John Hopcroft
To what extent is the success of deep visualization due to the training? Could we do deep visualization using untrained, random weight networks? To address this issue, we explore n…