661 citations · 1.2k across the 12 of their papers we have counts for
12 papers
Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting
Hao Liu, Bin Chen, Bo Wang +3
Recently, many semi-supervised object detection (SSOD) methods adopt teacher-student framework and have achieved state-of-the-art results. However, the teacher network is tightly c…
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:…
MAT: A Multi-strength Adversarial Training Method to Mitigate Adversarial Attacks
Chang Song, Hsin-Pai Cheng, Huanrui Yang +5
Some recent works revealed that deep neural networks (DNNs) are vulnerable to so-called adversarial attacks where input examples are intentionally perturbed to fool DNNs. In this w…
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…
A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation
Chunpeng Wu, Wei Wen, Tariq Afzal +3
Recently, DNN model compression based on network architecture design, e.g., SqueezeNet, attracted a lot attention. No accuracy drop on image classification is observed on these ext…
Coordinating Filters for Faster Deep Neural Networks
Wei Wen, Cong Xu, Chunpeng Wu +3
Very large-scale Deep Neural Networks (DNNs) have achieved remarkable successes in a large variety of computer vision tasks. However, the high computation intensity of DNNs makes i…
Learning Structured Sparsity in Deep Neural Networks
Wei Wen, Chunpeng Wu, Yandan Wang +2
High demand for computation resources severely hinders deployment of large-scale Deep Neural Networks (DNN) in resource constrained devices. In this work, we propose a Structured S…
A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chip
Wei Wen, Chunpeng Wu, Yandan Wang +5
IBM TrueNorth chip uses digital spikes to perform neuromorphic computing and achieves ultrahigh execution parallelism and power efficiency. However, in TrueNorth chip, low quantiza…