Hi, welcome to my website!
I am a fifth-year Ph.D. student at MIT CSAIL, working with Prof. Phillip Isola and Prof. Josh Tenenbaum. My main research interests lie in the intersection of machine perception, learning and reasoning, mainly from the perspective of vision.
Prior to MIT, I completed my M.Phil degree at CUHK, advised by Prof. Xiaoou Tang and Prof. Xiaogang Wang. I did my undergraduate study at Tsinghua University.
June, 2020: Gave a talk about Contrastive Learning at MIT Vision Seminar, find the Video Recording.
May, 2020: A PyTorch library of unsupervised contrastive learning approaches is released, see Github.
April, 2020: PyTorch code for SupContrast and SimCLR, see Repo.
Training-Free Uncertainty Estimation for Neural Networks
Lu Mi, Hao Wang, Yonglong Tian, Nir Shavit
arXiv:1910.04858
arXiv
What Makes for Good Views for Contrastive Learning?
Yonglong Tian, Chen Sun, Ben Poole, Dilip Krishnan, Cordelia Schmid, Phillip Isola
Advances In Neural Information Processing Systems (NeurIPS), 2020
arXiv
Project Page
Code
Google AI Blog
Supervised Contrastive Learning
Prannay Khosla*, Piotr Teterwak*, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, Dilip Krishnan
Advances In Neural Information Processing Systems (NeurIPS), 2020
Paper
Code[PyTorch]
Code[TensorFlow]
Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?
Yonglong Tian*, Yue Wang*, Dilip Krishnan, Joshua B. Tenenbaum, Phillip Isola
European Conference on Computer Vision (ECCV), 2020
Paper
Project Page
Code
Contrastive Multiview Coding
Yonglong Tian, Dilip Krishnan, Phillip Isola
arXiv:1906.05849
European Conference on Computer Vision (ECCV), 2020
Paper
Project Page
Code
Contrastive Representation Distillation
Yonglong Tian, Dilip Krishnan, Phillip Isola
arXiv:1910.10699
International Conference on Learning Representations (ICLR), 2020
Paper
arXiv
Project Page
Code
Contrastive Multiview Coding
Yonglong Tian, Dilip Krishnan, Phillip Isola
arXiv:1906.05849
Workshop on Self-supervised Learning (ICML workshop), 2019
arXiv
Project Page
Short version
Code
Learning to Infer and Execute 3D Shape Programs
Yonglong Tian, Andrew Luo, Xingyuan Sun, Kevin Ellis, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu
International Conference on Learning Representations (ICLR), 2019
Paper
Project Page
Poster
Code
ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees
Hao He, Hao Wang, Guang-He Lee, Yonglong Tian.
International Conference on Learning Representations (ICLR), 2019
Paper
Code
RF-Based Fall Monitoring Using Convolutional Neural Networks
Yonglong Tian*, Guang-He Lee*, Hao He*, Chen-Yu Hsu, Dina Katabi.
ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp/IMWUT), 2018
Paper
Slides
Project Page
RF-Based 3D Skeletons
Mingmin Zhao, Yonglong Tian, Hang Zhao, Mohammad Abu Alsheikh, Tianhong Li, Rumen Hristov, Zachary Kabelac, Dina Katabi, Antonio Torralba.
Special Interest Group on Data Communications (SIGCOMM), 2018
Paper
Project Page
Video
Bayesian Modelling and Monte Carlo Inference for GAN
Hao He, Hao Wang, Guang-He Lee, Yonglong Tian.
Theoretical Foundations and Applications of Deep Generative Models (ICML workshop), 2018
Paper
Representation Learning on Graphs with Jumping Knowledge Networks
Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, Stefanie Jegelka.
International Conference on Machine Learning (ICML), 2018
Paper
Supplementary
Through-Wall Human Pose Estimation Using Radio Signals
Mingmin Zhao, Tianhong Li, Mohammad Alsheikh, Yonglong Tian, Hang Zhao, Dina Katabi, Antonio Torralba.
Computer Vision and Pattern Recognition (CVPR), 2018
Paper
Project Page
Poster
Video
MIT News
DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks
Wanli Ouyang, Xingyu Zeng, Xiaogang Wang, Shi Qiu, Ping Luo, Yonglong Tian, et. al.
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017
Paper
Project Page
Deep Learning Strong Parts for Pedestrian Detection
Yonglong Tian, Ping Luo, Xiaogang Wang, Xiaoou Tang.
International Conference on Computer Vision (ICCV), 2015
Paper
Poster
Pedestrian Detection aided by Deep Learning Semantic Tasks
Yonglong Tian, Ping Luo, Xiaogang Wang, Xiaoou Tang.
Computer Vision and Pattern Recognition (CVPR), 2015
Paper
Poster
Project Page
DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
Wanli Ouyang, Xiaogang Wang, Xingyu Zeng, Shi Qiu, Ping Luo, Yonglong Tian, et. al.
Computer Vision and Pattern Recognition (CVPR), 2015
Paper
arXiv
Project Page
Switchable Deep Network for Pedestrian Detection
Yonglong Tian*, Ping Luo*, Xiaogang Wang, Xiaoou Tang.
Computer Vision and Pattern Recognition (CVPR), 2014
Paper
Video
Supplementary