6 papers
MVStylizer: An Efficient Edge-Assisted Video Photorealistic Style Transfer System for Mobile Phones
Ang Li, Chunpeng Wu, Yiran Chen +1
Recent research has made great progress in realizing neural style transfer of images, which denotes transforming an image to a desired style. Many users start to use their mobile p…
Regularized Training and Tight Certification for Randomized Smoothed Classifier with Provable Robustness
Huijie Feng, Chunpeng Wu, Guoyang Chen +2
Recently smoothing deep neural network based classifiers via isotropic Gaussian perturbation is shown to be an effective and scalable way to provide state-of-the-art probabilistic…
Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
Chunpeng Wu, Wei Wen, Yiran Chen +1
Generative adversarial network (GAN) has greatly improved the quality of unsupervised image generation. Previous GAN-based methods often require a large amount of high-quality trai…
Towards Leveraging the Information of Gradients in Optimization-based Adversarial Attack
Jingyang Zhang, Hsin-Pai Cheng, Chunpeng Wu +2
In recent years, deep neural networks demonstrated state-of-the-art performance in a large variety of tasks and therefore have been adopted in many applications. On the other hand,…
SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning
Wei Wen, Yandan Wang, Feng Yan +4
In Deep Learning, Stochastic Gradient Descent (SGD) is usually selected as a training method because of its efficiency; however, recently, a problem in SGD gains research interest:…
TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
Wei Wen, Cong Xu, Feng Yan +4
High network communication cost for synchronizing gradients and parameters is the well-known bottleneck of distributed training. In this work, we propose TernGrad that uses ternary…