Kaiming He δ½•ζΊζ˜Ž

  Research Scientist

  Facebook AI Research (FAIR), Menlo Park, CA

 

I am a Research Scientist at Facebook AI Research (FAIR) as of August 2016. Formerly I was a Lead Researcher at Microsoft Research Asia (MSRA), which I joined in 2011 after receiving the PhD degree. Prior to that, I had been an intern at MSRA since 2007 when receiving the B.S. degree. My research interests are on computer vision and deep learning. I have received 2 CVPR Best Paper Awards as the first author (2009 and 2016). I and colleagues developed Deep Residual Networks (ResNets) that won the 1st places in all five major tracks in ImageNet and MS COCO competitions 2015.


Internship:
I am looking for winter interns at FAIR, working on computer vision and deep learning.

News: Won CVPR Best Paper Award for the second time!


I am invited to give a Tutorial on Deep Residual Networks at ICML 2016.
 website

I served as an Area Chair for CVPR 2016.

I co-organized a Tutorial on Object Detection at ICCV 2015. slides

 

Single Image Haze Removal

Guided Image Filtering

 

Publications

Google Scholar Profile

   

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

   

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

   

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   code

   

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   code

   

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   code

   

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

 γ€€

Awards and Honor

 

Professional Activities

 

HTML Counter unique visitors since May 2009

Last update: Aug. 2016