Kaiming He 何恺明

  Research Scientist

  Facebook AI Research (FAIR), Menlo Park, CA

 

I joined Facebook AI Research (FAIR) in 2016 as a Research Scientist. Formerly I was with Microsoft Research Asia (MSRA), which I joined in 2011 after receiving my PhD. My research interests are in computer vision and deep learning.

I have received the Best Paper Award in CVPR 2009, CVPR 2016, and ICCV 2017 (Marr Prize) as the first author, and the Best Student Paper Award in ICCV 2017 as a co-mentor.
I and colleagues developed Deep Residual Networks (ResNets), currently the prevalent architecture in computer vision. ResNets have also been adopted in machine translation, speech synthesis, speech recognition, and AlphaGo.

I am looking for interns to work on computer vision and deep learning at FAIR in 2018.

According to Google Scholar Metrics, as of June 2017:


Activities


Publications

Google Scholar Profile

   

Data Distillation: Towards Omni-Supervised Learning
Ilija Radosavovic, Piotr Dollár, Ross Girshick, Georgia Gkioxari, and Kaiming He
Tech report, arXiv, Dec. 2017
arXiv

   

Learning to Segment Every Thing
Ronghang Hu, Piotr Dollár, Kaiming He, Trevor Darrell, and Ross Girshick
Tech report, arXiv, Nov. 2017
arXiv

   

Non-local Neural Networks
Xiaolong Wang, Ross Girshick, Abhinav Gupta, and Kaiming He
Tech report, arXiv, Nov. 2017
arXiv

   

Mask R-CNN
Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick
IEEE International Conference on Computer Vision (ICCV), 2017 (Oral). ICCV Best Paper Award (Marr Prize)
arXiv
   talk   slides: ICCV tutorial  ICCV oral  COCO workshop

   

Focal Loss for Dense Object Detection
Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár
IEEE International Conference on Computer Vision (ICCV), 2017 (Oral). ICCV Best Student Paper Award
arXiv

   

Transitive Invariance for Self-supervised Visual Representation Learning
Xiaolong Wang, Kaiming He, and Abhinav Gupta
IEEE International Conference on Computer Vision (ICCV), 2017
arXiv

   

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Priya Goyal, Piotr Dollár, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He
Tech report, arXiv, June
2017
arXiv

   

Detecting and Recognizing Human-Object Interactions
Georgia Gkioxari, Ross Girshick, Piotr Dollár, and Kaiming He
Tech report, arXiv, Apr.
2017
arXiv

   

Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
arXiv

   

Aggregated Residual Transformations for Deep Neural Networks
Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, and Kaiming He
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
arXiv
   code/models

   

R-FCN: Object Detection via Region-based Fully Convolutional Networks
Jifeng Dai, Yi Li, Kaiming He, and Jian Sun
Conference on Neural Information Processing Systems (NIPS), 2016
arXiv
   code

   

Is Faster R-CNN Doing Well for Pedestrian Detection?
Liliang Zhang, Liang Lin, Xiaodan Liang, and Kaiming He
European Conference on Computer Vision (ECCV), 2016

arXiv
   code

   

Instance-sensitive Fully Convolutional Networks
Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, and Jian Sun
European Conference on Computer Vision (ECCV), 2016

arXiv

   

Identity Mappings in Deep Residual Networks
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun
European Conference on Computer Vision (ECCV), 2016 (Spotlight)
arXiv   code

   

Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Oral). CVPR Best Paper Award
arXiv   code/models   talk
   slides: ILSVRC workshop  ICML tutorial  CVPR oral
ILSVRC & COCO competitions 2015: we won the 1st places in ImageNet classification, ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation!

   

Instance-aware Semantic Segmentation via Multi-task Network Cascades
Jifeng Dai, Kaiming He, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Oral)
arXiv
   code
1st place of COCO 2015 segmentation competition

   

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Di Lin, Jifeng Dai, Jiaya Jia, Kaiming He, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Oral)
arXiv   project

   

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016
arXiv

   

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun

Conference on Neural Information Processing Systems (NIPS), 2015
arXiv   NIPS version   code-matlab   code-python

   

Accelerating Very Deep Convolutional Networks for Classification and Detection
Xiangyu Zhang, Jianhua Zou, Kaiming He, and Jian Sun

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015
arXiv

   

Image Super-Resolution Using Deep Convolutional Networks
Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015
arXiv   code

waifu2x

   

Object Detection Networks on Convolutional Feature Maps
Shaoqing Ren, Kaiming He, Ross Girshick, Xiangyu Zhang, and Jian Sun

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted
arXiv

   

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
Jifeng Dai, Kaiming He, and Jian Sun
IEEE International Conference on Computer Vision (ICCV), 2015
arXiv

   

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun

IEEE International Conference on Computer Vision (ICCV), 2015
arXiv   ICCV version

The first to surpass human-level performance

   

Convolutional Neural Networks at Constrained Time Cost
Kaiming He and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
arXiv

   

Convolutional Feature Masking for Joint Object and Stuff Segmentation
Jifeng Dai, Kaiming He, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
arXiv
   code

   

Efficient and Accurate Approximations of Nonlinear Convolutional Networks
Xiangyu Zhang, Jianhua Zou, Xiang Ming, Kaiming He, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
arXiv

   

Sparse Projections for High-Dimensional Binary Codes
Yan Xia, Kaiming He, Pushmeet Kohli, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
paper   code

   

A Geodesic-Preserving Method for Image Warping
Dongping Li, Kaiming He, Jian Sun, and Kun Zhou
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
paper

   

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015
arXiv

100x faster than R-CNN for object detection

   

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun
European Conference on Computer Vision (ECCV), 2014
arXiv  
project   slides   poster   code
ILSVRC 2014 - We ranked 2nd in detection and 3rd in classification.

   

Learning a Deep Convolutional Network for Image Super-Resolution
Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang
European Conference on Computer Vision (ECCV), 2014
paper   code
waifu2x

   

Graph Cuts for Supervised Binary Coding
Tiezheng Ge, Kaiming He, and Jian Sun
European Conference on Computer Vision (ECCV), 2014
paper

   

Image Completion Approaches using the Statistics of Similar Patches
Kaiming He and Jian Sun
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014
paper   project

   

Product Sparse Coding
Tiezheng Ge, Kaiming He, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
paper

   

Optimized Product Quantization
Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014
paper   project

   

Content-Aware Rotation
Kaiming He, Huiwen Chang, and Jian Sun
IEEE International Conference on Computer Vision (ICCV), 2013
paper   image   project

   

Joint Inverted Indexing
Yan Xia,
Kaiming He, Fang Wen, and Jian Sun
IEEE International Conference on Computer Vision (ICCV), 2013
paper   project

   

Constant Time Weighted Median Filtering for Stereo Matching and Beyond
Ziyang Ma, Kaiming He, Yichen Wei, Jian Sun, and Enhua Wu
IEEE International Conference on Computer Vision (ICCV), 2013

paper   supp   code

   

Rectangling Panoramic Images via Warping
Kaiming He, Huiwen Chang, and Jian Sun
ACM Transactions on Graphics, Proceedings of ACM SIGGRAPH, 2013
paper   image   slides   project

   

Optimized Product Quantization for Approximate Nearest Neighbor Search
Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013
paper   supp   code   project

   

K-means Hashing: an Affinity-Preserving Quantization Method for Learning Binary Compact Codes
Kaiming He, Fang Wen, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013
paper 

   

Guided Image Filtering
Kaiming He, Jian Sun, and Xiaoou Tang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2013
paper   project

   

Statistics of Patch Offsets for Image Completion
Kaiming He and Jian Sun
European Conference on Computer Vision (ECCV), 2012
paper   supp  
project

   

Computing Nearest-Neighbor Fields via Propagation-Assisted KD-Trees
Kaiming He and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012
paper   poster

   

A Global Sampling Method for Alpha Matting
Kaiming He
, Christoph Rhemann, Carsten Rother, Xiaoou Tang, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011
paper

   

Single Image Haze Removal using Dark Channel Prior
Kaiming He, Jian Sun, and Xiaoou Tang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2010
Spotlight Paper for TPAMI Dec. 2011 issue
paper

   

Guided Image Filtering
Kaiming He
, Jian Sun, and Xiaoou Tang
European Conference on Computer Vision (ECCV), 2010 (Oral)
paper   supp   code   slides   project

   

Fast Matting using Large Kernel Matting Laplacian Matrices
Kaiming He, Jian Sun, and Xiaoou Tang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010
paper   supp

   

Single Image Haze Removal using Dark Channel Prior
Kaiming He, Jian Sun, and Xiaoou Tang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009 (Oral).
CVPR Best Paper Award
paper   images   slides   videos  
project   thesis

  

Awards and Honors

 
  HTML
          Counter unique visitors since May 2009

Last update: Dec. 2017