Yu Fengwei (Forwil)
Vice Research Director
Sensetime Research - Model Toolchain Team
Github / Google scholar / CV


I'm diving in in deep learning industrialization. Here is the areas I am interested in

  • High performance computing
  • Neural Network Compiler
  • Vision DataBase
  • Neural Network Deployment, Porting and Inference
  • Model Quantization and Sparity
  • Network Architect
  • Large Scale Training
  • You can find our opensource project in Github ModelTC group. And find tech blog on Zhihu 踢翻炼丹炉


    We are now hiring self-motivation intern and full-time research. If you are looking for some ML-system jobs please feel free to e-mail me (forwil@foxmail.com) !

  • [2022] 1 papers accpeted by ICPP2022! code is available NNLQP
  • [2022] 1 papers accpeted by CVPR2022!
  • [2022] 2 papers accpeted by ICLR2022!
  • [2021] My team won championship of LPCVC 2021 FPGA Track, we also opensource our solution.
  • [2021] We are also release one benchmark with code MQbench and one opensource project EOD.
  • [2021] 7 papers accepted by ICLR/CVPR/NeurIPS/ICCV 2021!
  • [2020] 4 papers accepted by ICPP/CVPR/ICLR in 2020!
  • [2019] 1 papers accepted by ICCV in 2019 !
  • [2016] We win the 1st place in ECCV-MOT16 Challenge! data
  • [2016] 1 papers accepted by ECCV in 2016 !
  • About me / bio

    Fengwe Yu is now a vice research director and team leader of Model-ToolChain Team of Sensetime Research under the supervisor of Prof. Wang-Xiaogang and Dr. Yan-Junjie , working on deep learning system.

    He enjoy 2-years full-time internship in STVIR on developing high-performance video face/vehicle/pedestrian analysis system and porting algorithm into embedded system.

    Before join sensetime, He lead BUAA HPC team get first-prize on ASC Student Supercomputer Challenge 2015 and spend half an year intership on Microsoft IOT team Beijing to develop R485 bus communication protocal.

    He received a Master and B.S. in computer science from the Beihang University under the supervision of xiaohua shi on JVM memory profiling/compcert/language model in 2018 and 2015.


    NNLQP: A Multi-Platform Neural Network Latency Query and Prediction System with An Evolving Database PDF
    2022 International Conference on Parallel Processing(ICPP)
    Liang Liu, Mingzhu Shen, Ruihao Gong, Fengwei Yu , Hailong Yang
    QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization PDF
    2022 International Conference on Learning Representations(ICLR)
    Xiuying Wei, Ruihao Gong, Yuhang Li, Xianglong Liu, Fengwei Yu
    Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm PDF
    2022 International Conference on Learning Representations(ICLR)
    Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, Junjie Yan
    Once Quantization-Aware Training: High Performance Extremely Low-Bit Architecture Search PDF
    2021 International Conference on Computer Vision(ICCV)
    Mingzhu Shen, Feng Liang, Ruihao Gong, Yuhang Li, Chuming Li, Chen Lin, Fengwei Yu, Junjie Yan, Wanli Ouyang
    Differentiable Dynamic Wirings for Neural Networks PDF
    2021 International Conference on Computer Vision(ICCV)
    Kun Yuan, Quanquan Li, Shaopeng Guo, Dapeng Chen, Aojun Zhou,Fengwei Yu , Ziwei Liu
    MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing PDF
    2021 International Conference on Computer Vision(ICCV)
    Yuhang Li, Feng Zhu, Ruihao Gong, Mingzhu Shen, Xin Dong, Fengwei Yu, Shaoqing Lu, Shi Gu
    Incorporating convolution designs into visual transformers PDF
    2021 International Conference on Computer Vision(ICCV)
    Kun Yuan, Shaopeng Guo, Ziwei Liu, Aojun Zhou, Fengwei Yu , Wei Wu
    MQBench: Towards Reproducible and Deployable Model Quantization Benchmark PDF
    2021 h Conference on Neural Information Processing Systems (NeurIPS)
    Yuhang Li, Mingzhu Shen, Jian Ma, Yan Ren, Mingxin Zhao, Qi Zhang, Ruihao Gong, Fengwei Yu, Junjie Yan
    Diversifying Sample Generation for Accurate Data-Free Quantization PDF
    2021 Conference on Computer Vision and Pattern Recognition(CVPR)
    Xiangguo Zhang, Haotong Qin, Yifu Ding, Ruihao Gong, Qinghua Yan, Renshuai Tao, Yuhang Li, Fengwei Yu, Xianglong Liu
    BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction PDF
    2021 International Conference on Learning Representations(ICLR)
    Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu , Wei Wang, Shi Gu
    Extremely Low-bit Convolution Optimization for Quantized Neural Network on Modern Computer Architectures PDF
    2020 International Conference on Parallel Processing (ICPP)
    Qingchang Han, Yongmin Hu, Fengwei Yu , Hailong Yang, Bing Liu, Peng Hu, Ruihao Gong, Yanfei Wang, Rui Wang, Zhongzhi Luan, Depei Qian
    DMS: Differentiable Dimension Search for Binary Neural Networks PDF
    2020 International Conference on Learning Representations (ICLR) NAS workshop
    Yuhang Li, Ruihao Gong, Fengwei Yu, Xin Dong, Xianglong Liu
    Towards Unified INT8 Training for Convolutional Neural Network PDF
    2020 Conference on Computer Vision and Pattern Recognition (CVPR)
    Feng Zhu, Ruihao Gong, Fengwei Yu, Xianglong Liu, Yanfei Wang, Zhelong Li, Xiuqi Yang, Junjie Yan
    Forward and Backward Information Retention for Accurate Binary Neural Networks PDF
    2020 Conference on Computer Vision and Pattern Recognition (CVPR)
    Haotong Qin, Ruihao Gong, Xianglong Liu, Mingzhu Shen, Ziran Wei, Fengwei Yu, Jingkuan Song
    Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks PDF
    2019 International Conference in Computer Vision (ICCV)
    Ruihao Gong, Xianglong Liu, Shenghu Jiang, Tianxiang Li, Peng Hu, Jiazhen Lin, Fengwei Yu, Junjie Yan.
    POI: Multiple Object Tracking with High Performance Detection and Appearance Feature PDF
    2016 European Conference on Computer Vision (ECCV) workshop
    Fengwei Yu, Wenbo Li, Quanquan Li, Yu Liu, Xiaohua Shi, Junjie Yan

    I like this website