Sheng Xu

I am a PhD candidate (2018.09-) at the School of Automation Science and Electrical Engineering, Beihang University, supervised by Prof. Jinhu Lu and Prof. Baochang Zhang. I obtained my BSc degree in School of Transportation Science and Engineering from Beihang University (2014.09-2018.06). I was interned at Shanghai AI Lab (2021.12-2023.02), and VIS department of Baidu Inc. (2020.05-2020.12).

Email: shengxu@buaa.edu.cn

Google Scholar / Github

Research

My area of interest lies in the techniques of network binarization and quantization, along with knowledge distillation. My research objective is to facilitate the deployment of advanced neural network models on hardware with limited resources. This involves compressing various neural architectures and ensuring their adaptable deployment on diverse hardware platforms. My research focus is mainly on:

Network binarization and quantization

Knowledge distillation

Image synthesizing

Object detection

Selected Publications

Full list can be found on Google Scholar.

	Q-DETR: An Efficient Low-Bit Quantized Detection Transformer Sheng Xu^, Yanjing Li^, Mingbao Lin, Peng Gao, Guodong Guo, Jinhu Lu, Baochang Zhang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Highlight presentation [Paper coming] / [arXiv coming] / [code coming] / (^ Equal Contribution)*
	Implicit Diffusion Models for Continuous Super-Resolution Sicheng Gao^, Xuhui Liu^, Bohan Zeng^, Sheng Xu*, Yanjing Li, Xiaoyan Luo, Jianzhuang Liu, Xiantong Zhen, Baochang Zhang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [Paper coming] / [arXiv coming] / [code coming]
	Resilient Binary Neural Network Sheng Xu^, Yanjing Li^, Teli Ma^, Mingbao Lin, Hao Dong, Baochang Zhang, Peng Gao, Jinhu Lu AAAI Conference on Artificial Intelligence (AAAI), 2023 Oral presentation* [Paper coming] / [arXiv] / [code] (^* Equal Contribution)
	Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer Yanjing Li^, Sheng Xu^, Baochang Zhang, Xianbin Cao, Peng Gao, Guodong Guo Conference on Neural Information Processing Systems (NeurIPS), 2022 [Paper] / [arXiv] / [code] (^* Equal Contribution)
	Recurrent Bilinear Optimization for Binary Neural Networks Sheng Xu^, Yanjing Li^, Tiancheng Wang, Teli Ma, Baochang Zhang, Peng Gao, Yu Qiao, Jinhu Lv, Guodong Guo European Conference on Computer Vision (ECCV), 2022 Oral presentation [Paper] / [arXiv] / [code] (^* Equal Contribution)
	IDa-Det: An Information Discrepancy-aware Distillation for 1-bit Detectors Sheng Xu^, Yanjing Li^, Bohan Zeng^, Baochang Zhang, Xianbin Cao, Peng Gao, Jinhu Lv European Conference on Computer Vision (ECCV), 2022 [Paper] / [arXiv] / [code] (^ Equal Contribution)
	Layer-wise Searching for 1-bit Detectors Sheng Xu, Junhe Zhao, Jinhu Lu, Baochang Zhang, Shumin Han, David Doermann IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Oral presentation [Paper]

Academic Services

Conference Reviewer:

IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2022--2023.
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
European Conference on Computer Vision (ECCV), 2022.
International Conference on Machine Learning (ICML), 2022.
Conference on Neural Information Processing Systems (NeurIPS), 2022--2023.

Journal Reviewer:

IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT).
Science China Information Sciences (SCIS).