peisong.wang@nlpr.ia.ac.cn
北京市海淀区中关村东路95号
深度学习高效计算
王培松,中国科学院自动化研究所复杂系统认知与决策实验室副研究员,硕导。2013年在山东大学获得学士学位,2018年在中国科学院大学获得博士学位。目前主要从事高效智能计算、神经网络加速与压缩等方面的研究。在IEEE TPAMI、TNNLS、ICML、CVPR、ICCV、ECCV等国际期刊和会议发表论文40余篇。主持国家自然科学基金青年基金、中科院战略先导子课题,参与国家重点研发计划、基金重点、以及华为、阿里巴巴、三星等多项科研项目。曾获Nvidia奖学金、IEEE国际标准突出贡献奖、NeurIPS国际神经网络压缩竞赛MicroNet Challenge冠军,入选中科院特聘研究骨干、北京市科协青年人才托举工程、微软亚洲研究院“铸星计划”、CCF-百度松果基金学者等。
2024
[1] Peisong Wang, Xiangyu He, Jian Cheng. Toward Accurate Binarized Neural Networks with Sparsity for Mobile Application. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol.35, No.1, pp.272-284,2024.
[2] Zeyu Zhu, Peisong Wang, Qinghao Hu, Gang Li, Xiaoyao Liang, Jian Cheng. FastGL: A GPU-Efficient Framework for Accelerating Sampling-based GNN Training at Large Scale. ACM ASPLOS 2024.
[3] Zhengyang Zhuge, Jiaxing Wang, Yong Li, Yongjun Bao, Peisong Wang, Jian Cheng. Patch-Aware Sample Selection for Efficient Masked Image Modeling. AAAI 2024.
[4] Zhengyang Zhuge, Peisong Wang, Xingting Yao, Jian Cheng. Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration. ICML 2024.
2023
[2] Peisong Wang, Weihan Chen, Xiangyu He, Qiang Chen, Qingshan Liu, Jian Cheng. Optimization-based Post-training Quantization with Bit-split and Stitching. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol.45, No.2, pp.2119-2135, 2023.
[3] Peisong Wang*, Fanrong Li*, Gang Li, Jian Cheng. Extremely Sparse Networks via Binary Augmented Pruning for Fast Image Classification. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Vol.34, No.8, pp.4167-4180, 2023.
[4] Weixiang Xu*, Fanrong Li*, Yingying Jiang, Yong A, Xiangyu He, Peisong Wang, Jian Cheng. Improving Extreme Low-bit Quantization with Soft Threshold. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol.33, No.4, pp.1549-1543, 2023.
[5] Weihan Chen, Peisong Wang, Jian Cheng. Towards Automatic Model Compression via a Unified Two-Stage Framework. Pattern Recognition (PR), Vol.140, 2023.
[6] Tianqi Chen, Weixiang Xu, Weihan Chen, Peisong Wang, Jian Cheng. Towards Efficient and Accurate Winograd Convolution via Full Quantization. NeurIPS 2023.
2022
[1] Anda Cheng, Peisong Wang, Xi Sheryl Zhang, Jian Cheng. Differentially Private Federated Learning with Local Regularization and Sparsification. CVPR, 2022.
[2] Weixiang Xu, Xiangyu He, Ke Cheng, Peisong Wang, Jian Cheng. Towards Fully Sparse Training: Information Restoration with Spatial Similarity. AAAI, 2022.
[3] Anda Cheng, Jiaxing Wang, Xi Sheryl Zhang, Qiang Chen, Peisong Wang, Jian Cheng. Dpnas: Neural architecture search for deep learning with differential privacy. AAAI, 2022.
2021
[1] Peisong Wang*, Fanrong Li*, Gang Li, Jian Cheng. Extremely Sparse Networks via Binary Augmented Pruning for Fast Image Classification. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021.
[2] Weihan Chen, Peisong Wang, Jian Cheng. Towards mixed-precision quantization of neural networks via constrained optimization. ICCV, 2021.
2020
[1] Peisong Wang, Xiangyu He, Qiang Chen, Anda Cheng, Qingshan Liu and Jian Cheng. Unsupervised Network Quantization via Fixed-point Factorization. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020.
[2] Qiang Chen, Anda Cheng, Xiangyu He, Peisong Wang, Jian Cheng. Spatialflow: Bridging all tasks for panoptic segmentation. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020.
[3] Qiang Chen, Peisong Wang, Anda Cheng, Wanguo Wang, Yifan Zhang, Jian Cheng. Robust one-stage object detection with location-aware classifiers. Pattern Recognition (PR), 2020.
[4] Peisong Wang, Qiang Chen, Xiangyu He and Jian Cheng. Towards Accurate Post-training Network Quantization via Bit-Split and Stitching. ICML, 2020.
[5] Peisong Wang*, Xiangyu He*, Gang Li, Tianli Zhao and Jian Cheng. Sparsity-Inducing Binarized Neural Networks. AAAI, 2020.
[6] Gang Li, Peisong Wang, Zejian Liu, Cong Leng, Jian Cheng. Hardware acceleration of CNN with one-hot quantization of weights and activations. DATE, 2020.
[7] Weixiang Xu, Xiangyu He, Tianli Zhao, Qinghao Hu, Peisong Wang, Jian Cheng. Soft Threshold Ternary Networks. IJCAI, 2020.
[8] Xiangyu He, Zitao Mo, Ke Cheng, Weixiang Xu, Qinghao Hu, Peisong Wang, Qingshan Liu, Jian Cheng. Proxybnn: Learning binarized neural networks via proxy matrices. ECCV, 2020.
[9] Weihan Chen, Peisong Wang, Jian Cheng. Towards Convolutional Neural Networks Compression via Global&Progressive Product Quantization. BMVC, 2020.
2019
[1] Xiangyu He, Peisong Wang, Jian Cheng. K-nearest neighbors hashing. CVPR, 2019.
[2] Xiangyu He, Zitao Mo, Peisong Wang, Yang Liu, Mingyuan Yang, Jian Cheng. Ode-inspired network design for single image super-resolution. CVPR, 2019.
[3] Zhe Li, Peisong Wang, Hanqing Lu, Jian Cheng. Reading selectively via Binary Input Gated Recurrent Unit. IJCAI, 2019.
2018及以前
[1] Peisong Wang, Qinghao Hu, Zhiwei Fang, Chaoyang Zhao and Jian Cheng. DeepSearch: A fast image search framework for mobile devices. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2018.
[2] Jian Cheng, Peisong Wang, Gang Li, Qing-hao Hu, Hanqing Lu. Recent advances in efficient computation of deep convolutional neural networks. Frontiers of Information Technology & Electronic Engineering (FITEE), 2018.
[3] Peisong Wang, Qinghao Hu, Yifang Zhang, Chunjie Zhang, Yang Liu and Jian Cheng. Two-Step Quantization for Low-bit Neural Networks. CVPR, 2018.
[4] Qinghao Hu, Peisong Wang, Jian Cheng. From hashing to cnns: Training binary weight networks via hashing. AAAI, 2018.
[5] Qinghao Hu, Gang Li, Peisong Wang, Yifan Zhang, Jian Cheng. Training binary weight networks via semi-binary decomposition. ECCV, 2018.
[6] Guibo Zhu, Jinqiao Wang, Peisong Wang, Yi Wu, Hanqing Lu. Feature distilled tracking. IEEE transactions on cybernetics, 2017.
[7] Peisong Wang and Jian Cheng. Fixed-point Factorized Networks. CVPR, 2017.
[8] Peisong Wang, Qiang Song, Hua Han, Jian Cheng. Sequentially supervised long short-term memory for gesture recognition. Cognitive Computation, 2016.
[9] Peisong Wang and Jian Cheng. Accelerating Convolutional Neural Networks for Mobile Applications. ACM Multimedia, 2016.
2023 入选CCF-百度松果基金学者
2023 入选中科院特聘研究骨干
2022 入选北京科协青年人才托举工程
2022 获得IEEE国际标准突出贡献奖
2022 获得ECCV AIM: Reversed ISP Challenge季军
2021 入选微软亚洲研究院“铸星计划”
2019 获得NeurIPS 2019国际神经网络压缩挑战赛MicroNet Challenge冠军
2018 获得NVIDIA奖学金