Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Guangrun Wang

Guangrun Wang

Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

Nov 27, 2022
Guangrun Wang, Philip H. S. Torr

Figure 1 for Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

Figure 2 for Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

Figure 3 for Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

Figure 4 for Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

* This paper has 29 pages with 22 figures, including rich supplementary information

Access Paper or Ask Questions

Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing

Aug 08, 2022
Guangcong Wang, Guangrun Wang, Wenqi Liang, Jianhuang Lai

Figure 1 for Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing

Figure 2 for Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing

Figure 3 for Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing

Figure 4 for Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing

* Weight Similarity of Neural Networks

Access Paper or Ask Questions

Beyond Fixation: Dynamic Window Visual Transformer

Apr 08, 2022
Pengzhen Ren, Changlin Li, Guangrun Wang, Yun Xiao, Qing Du, Xiaodan Liang, Xiaojun Chang

Figure 1 for Beyond Fixation: Dynamic Window Visual Transformer

Figure 2 for Beyond Fixation: Dynamic Window Visual Transformer

Figure 3 for Beyond Fixation: Dynamic Window Visual Transformer

Figure 4 for Beyond Fixation: Dynamic Window Visual Transformer

* CVPR2022

Access Paper or Ask Questions

Automated Progressive Learning for Efficient Training of Vision Transformers

Mar 28, 2022
Changlin Li, Bohan Zhuang, Guangrun Wang, Xiaodan Liang, Xiaojun Chang, Yi Yang

Figure 1 for Automated Progressive Learning for Efficient Training of Vision Transformers

Figure 2 for Automated Progressive Learning for Efficient Training of Vision Transformers

Figure 3 for Automated Progressive Learning for Efficient Training of Vision Transformers

Figure 4 for Automated Progressive Learning for Efficient Training of Vision Transformers

* Accepted to CVPR 2022

Access Paper or Ask Questions

EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation

Sep 16, 2021
Chenhe Dong, Guangrun Wang, Hang Xu, Jiefeng Peng, Xiaozhe Ren, Xiaodan Liang

Figure 1 for EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation

Figure 2 for EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation

Figure 3 for EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation

Figure 4 for EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation

* Findings of EMNLP 2021

Access Paper or Ask Questions

Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

Aug 22, 2021
Jiefeng Peng, Jiqi Zhang, Changlin Li, Guangrun Wang, Xiaodan Liang, Liang Lin

Figure 1 for Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

Figure 2 for Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

Figure 3 for Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

Figure 4 for Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

* Accepted to ICCV 2021

Access Paper or Ask Questions

Solving Inefficiency of Self-supervised Representation Learning

Apr 18, 2021
Guangrun Wang, Keze Wang, Guangcong Wang, Phillip H. S. Torr, Liang Lin

Figure 1 for Solving Inefficiency of Self-supervised Representation Learning

Figure 2 for Solving Inefficiency of Self-supervised Representation Learning

Figure 3 for Solving Inefficiency of Self-supervised Representation Learning

Figure 4 for Solving Inefficiency of Self-supervised Representation Learning

* 11 pages, 3 figures

Access Paper or Ask Questions