Picture for Hong Zhou

Hong Zhou

PTQD: Accurate Post-Training Quantization for Diffusion Models

May 18, 2023
Yefei He, Luping Liu, Jing Liu, Weijia Wu, Hong Zhou, Bohan Zhuang

* 10 pages, 4 figures

Access Paper or Ask Questions

Experimental Design for Any $p$-Norm

May 03, 2023
Lap Chi Lau, Robert Wang, Hong Zhou

* 29 pages

Access Paper or Ask Questions

BiViT: Extremely Compressed Binary Vision Transformer

Nov 14, 2022
Yefei He, Zhenyu Lou, Luoming Zhang, Weijia Wu, Bohan Zhuang, Hong Zhou

Figure 1 for BiViT: Extremely Compressed Binary Vision Transformer

Figure 2 for BiViT: Extremely Compressed Binary Vision Transformer

Figure 3 for BiViT: Extremely Compressed Binary Vision Transformer

Figure 4 for BiViT: Extremely Compressed Binary Vision Transformer

* Under review

Access Paper or Ask Questions

Binarizing by Classification: Is soft function really necessary?

May 16, 2022
Yefei He, Luoming Zhang, Weijia Wu, Hong Zhou

Figure 1 for Binarizing by Classification: Is soft function really necessary?

Figure 2 for Binarizing by Classification: Is soft function really necessary?

Figure 3 for Binarizing by Classification: Is soft function really necessary?

Figure 4 for Binarizing by Classification: Is soft function really necessary?

* submitted to NeurIPS2022

Access Paper or Ask Questions

Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization

Apr 08, 2022
Yefei He, Luoming Zhang, Weijia Wu, Hong Zhou

Figure 1 for Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization

Figure 2 for Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization

Figure 3 for Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization

Figure 4 for Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization

* submitted to ICML2022

Access Paper or Ask Questions

End-to-End Video Text Spotting with Transformer

Mar 20, 2022
Weijia Wu, Debing Zhang, Ying Fu, Chunhua Shen, Hong Zhou, Yuanqiang Cai, Ping Luo

Figure 1 for End-to-End Video Text Spotting with Transformer

Figure 2 for End-to-End Video Text Spotting with Transformer

Figure 3 for End-to-End Video Text Spotting with Transformer

Figure 4 for End-to-End Video Text Spotting with Transformer

* 10 pages, 5 figures

Access Paper or Ask Questions