3 citations · 5 across the 3 of their papers we have counts for
4 papers
Towards Speeding up Adversarial Training in Latent Spaces
Yaguan Qian, Qiqi Shao, Tengteng Yao +5
Adversarial training is wildly considered as one of the most effective way to defend against adversarial examples. However, existing adversarial training methods consume unbearable…
Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in GANs
Shaoning Zeng, Bob Zhang
In the generator of typical Generative Adversarial Networks (GANs), a noise is inputted to generate fake samples via a series of convolutional operations. However, current noise ge…
Two-stage Image Classification Supervised by a Single Teacher Single Student Model
Jianhang Zhou, Shaoning Zeng, Bob Zhang
The two-stage strategy has been widely used in image classification. However, these methods barely take the classification criteria of the first stage into consideration in the sec…
Collaboratively Weighting Deep and Classic Representation via L2 Regularization for Image Classification
Shaoning Zeng, Bob Zhang, Yanghao Zhang +1
Deep convolutional neural networks provide a powerful feature learning capability for image classification. The deep image features can be utilized to deal with many image understa…