Can Wang
Can Wang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Chun Chen
Zhejiang University, Hangzhou, China
1 shared publication - Defang Chen
University of California, Berkeley, Berkeley, USA
1 shared publication - Deshi Ye
College of Computer Science, Zhejiang University, Hangzhou, China
1 shared publication Jing Hou
1 shared publication- Jinhao Wang
Electric Power Research Institute of State Grid Shanxi Electirc Power Company, Taiyuan 030001, China
1 shared publication - Shiyu Liu
School of Materials and Physics China University of Mining and Technology Xuzhou 221116 China
1 shared publication
Latest Publications
- Open Access
- 1 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 810-815
Accelerating Diffusion Sampling with Classifier-based Feature Distillation
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of N-step teacher sampler with N/2-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed Classifier-based Feature Distillation (CFD). Instead of aligning output images, we distill teacher’s sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is available at https://github.com/zju-SWJ/RCFD.
- 1 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 810-815
Open AccessAccelerating Diffusion Sampling with Classifier-based Feature Distillation
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of N-step teacher sampler with N/2-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed Classifier-based Feature Distillation (CFD). Instead of aligning output images, we distill teacher’s sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is available at https://github.com/zju-SWJ/RCFD.
- Open Access
- 5 December 2022
- Published by Elsevier in Case Studies in Construction Materials
- Vol. 18
A 3D rotational silo-torus model for face stability analysis of circular tunnels
- 5 December 2022
- Published by Elsevier in Case Studies in Construction Materials
- Vol. 18
Open AccessA 3D rotational silo-torus model for face stability analysis of circular tunnels
- Open Access
- 12 December 2018
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 51 (28) , 55-60
Renewable Energy Accommodation Capability Evaluation of Power System with Wind Power and Photovoltaic Integration
- 12 December 2018
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 51 (28) , 55-60
Open AccessRenewable Energy Accommodation Capability Evaluation of Power System with Wind Power and Photovoltaic Integration