160 citations · 518 across the 23 of their papers we have counts for
23 papers
Robustifying Token Attention for Vision Transformers
Yong Guo, David Stutz, Bernt Schiele
Despite the success of vision transformers (ViTs), they still suffer from significant drops in accuracy in the presence of common corruptions, such as noise or blur. Interestingly,…
Boosting Semi-Supervised Learning with Contrastive Complementary Labeling
Qinyi Deng, Yong Guo, Zhibang Yang +2
Semi-supervised learning (SSL) has achieved great success in leveraging a large amount of unlabeled data to learn a promising classifier. A popular approach is pseudo-labeling that…
Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images
Bingna Xu, Yong Guo, Luoqian Jiang +2
Deep networks have achieved great success in image rescaling (IR) task that seeks to learn the optimal downscaled representations, i.e., low-resolution (LR) images, to reconstruct…
Improving Fine-tuning of Self-supervised Models with Contrastive Initialization
Haolin Pan, Yong Guo, Qinyi Deng +3
Self-supervised learning (SSL) has achieved remarkable performance in pretraining the models that can be further used in downstream tasks via fine-tuning. However, these self-super…
Improving Robustness by Enhancing Weak Subnets
Yong Guo, David Stutz, Bernt Schiele
Despite their success, deep networks have been shown to be highly susceptible to perturbations, often causing significant drops in accuracy. In this paper, we investigate model rob…
Contrastive Neural Architecture Search with Neural Architecture Comparators
Yaofo Chen, Yong Guo, Qi Chen +4
One of the key steps in Neural Architecture Search (NAS) is to estimate the performance of candidate architectures. Existing methods either directly use the validation performance…
Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets
Yong Guo, Yaofo Chen, Yin Zheng +5
Designing feasible and effective architectures under diverse computation budgets incurred by different applications/devices is essential for deploying deep models in practice. Exis…
Towards Accurate and Compact Architectures via Neural Architecture Transformer
Yong Guo, Yin Zheng, Mingkui Tan +5
Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically se…
Deep View Synthesis via Self-Consistent Generative Network
Zhuoman Liu, Wei Jia, Ming Yang +3
View synthesis aims to produce unseen views from a set of views captured by two or more cameras at different positions. This task is non-trivial since it is hard to conduct pixel-l…
Double Forward Propagation for Memorized Batch Normalization
Yong Guo, Qingyao Wu, Chaorui Deng +2
Batch Normalization (BN) has been a standard component in designing deep neural networks (DNNs). Although the standard BN can significantly accelerate the training of DNNs and impr…
Conditional Automated Channel Pruning for Deep Neural Networks
Yixin Liu, Yong Guo, Zichang Liu +5
Model compression aims to reduce the redundancy of deep networks to obtain compact models. Recently, channel pruning has become one of the predominant compression methods to deploy…
Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search
Yong Guo, Yaofo Chen, Yin Zheng +4
Neural architecture search (NAS) has become an important approach to automatically find effective architectures. To cover all possible good architectures, we need to search in an e…
Improving Generative Adversarial Networks with Local Coordinate Coding
Jiezhang Cao, Yong Guo, Qingyao Wu +3
Generative adversarial networks (GANs) have shown remarkable success in generating realistic data from some predefined prior distribution (e.g., Gaussian noises). However, such pri…
Disturbance-immune Weight Sharing for Neural Architecture Search
Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang +4
Neural architecture search (NAS) has gained increasing attention in the community of architecture design. One of the key factors behind the success lies in the training efficiency…
Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
Yong Guo, Jian Chen, Jingdong Wang +5
Deep neural networks have exhibited promising performance in image super-resolution (SR) by learning a nonlinear mapping function from low-resolution (LR) images to high-resolution…
Hierarchical Neural Architecture Search for Single Image Super-Resolution
Yong Guo, Yongsheng Luo, Zhenhao He +2
Deep neural networks have exhibited promising performance in image super-resolution (SR). Most SR models follow a hierarchical architecture that contains both the cell-level design…
Joint Wasserstein Distribution Matching
JieZhang Cao, Langyuan Mo, Qing Du +4
Joint distribution matching (JDM) problem, which aims to learn bidirectional mappings to match joint distributions of two domains, occurs in many machine learning and computer visi…
Discrimination-aware Network Pruning for Deep Model Compression
Jing Liu, Bohan Zhuang, Zhuangwei Zhuang +4
We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with…
Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
Yong Guo, Qi Chen, Jian Chen +3
Generating images via the generative adversarial network (GAN) has attracted much attention recently. However, most of the existing GAN-based methods can only produce low-resolutio…
Discrimination-aware Channel Pruning for Deep Neural Networks
Zhuangwei Zhuang, Mingkui Tan, Bohan Zhuang +5
Channel pruning is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimi…
Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss
Yong Guo, Qi Chen, Jian Chen +5
Deep neural networks have exhibited promising performance in image super-resolution (SR) due to the power in learning the non-linear mapping from low-resolution (LR) images to high…
Adversarial Learning with Local Coordinate Coding
Jiezhang Cao, Yong Guo, Qingyao Wu +3
Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of…
The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs
Yong Guo, Jian Chen, Qing Du +3
Depth is one of the key factors behind the success of convolutional neural networks (CNNs). Since ResNet, we are able to train very deep CNNs as the gradient vanishing issue has be…