Kaiming He

is this you? claim profile

∙ 0 followers
Facebook ∙ Microsoft

Research Scientist at Facebook AI Research

Graph Structure of Neural Networks

Neural networks are often represented as graphs of connections between n...
07/13/2020 ∙ by Jiaxuan You, et al. ∙ 23 ∙ share

read it
Designing Network Design Spaces

In this work, we present a new network design paradigm. Our goal is to h...
03/30/2020 ∙ by Ilija Radosavovic, et al. ∙ 8 ∙ share

read it
Are Labels Necessary for Neural Architecture Search?

Existing neural network architectures in computer vision — whether desig...
03/26/2020 ∙ by Chenxi Liu, et al. ∙ 14 ∙ share

read it
Improved Baselines with Momentum Contrastive Learning

Contrastive unsupervised learning has recently shown encouraging progres...
03/09/2020 ∙ by Xinlei Chen, et al. ∙ 9 ∙ share

read it
PointRend: Image Segmentation as Rendering

We present a new method for efficient high-quality image segmentation of...
12/17/2019 ∙ by Alexander Kirillov, et al. ∙ 28 ∙ share

read it
A Multigrid Method for Efficiently Training Video Models

Training competitive deep video models is an order of magnitude slower t...
12/02/2019 ∙ by Chao-Yuan Wu, et al. ∙ 7 ∙ share

read it
Momentum Contrast for Unsupervised Visual Representation Learning

We present Momentum Contrast (MoCo) for unsupervised visual representati...
11/13/2019 ∙ by Kaiming He, et al. ∙ 25 ∙ share

read it
Deep Hough Voting for 3D Object Detection in Point Clouds

Current 3D object detection methods are heavily influenced by 2D detecto...
04/21/2019 ∙ by Charles R. Qi, et al. ∙ 18 ∙ share

read it
Exploring Randomly Wired Neural Networks for Image Recognition

Neural networks for image recognition have evolved through extensive man...
04/02/2019 ∙ by Saining Xie, et al. ∙ 36 ∙ share

read it
TensorMask: A Foundation for Dense Object Segmentation

Sliding-window object detectors that generate bounding-box object predic...
03/28/2019 ∙ by Xinlei Chen, et al. ∙ 28 ∙ share

read it
Panoptic Feature Pyramid Networks

The recently introduced panoptic segmentation task has renewed our commu...
01/08/2019 ∙ by Alexander Kirillov, et al. ∙ 10 ∙ share

read it
Long-Term Feature Banks for Detailed Video Understanding

To understand the world, we humans constantly need to relate the present...
12/12/2018 ∙ by Chao-Yuan Wu, et al. ∙ 4 ∙ share

read it
SlowFast Networks for Video Recognition

We present SlowFast networks for video recognition. Our model involves (...
12/10/2018 ∙ by Christoph Feichtenhofer, et al. ∙ 0 ∙ share

read it
Feature Denoising for Improving Adversarial Robustness

Adversarial attacks to image classification systems present challenges t...
12/09/2018 ∙ by Cihang Xie, et al. ∙ 0 ∙ share

read it
Rethinking ImageNet Pre-training

We report competitive results on object detection and instance segmentat...
11/21/2018 ∙ by Kaiming He, et al. ∙ 8 ∙ share

read it
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations

Modern deep transfer learning approaches have mainly focused on learning...
06/14/2018 ∙ by Zhilin Yang, et al. ∙ 0 ∙ share

read it
Exploring the Limits of Weakly Supervised Pretraining

State-of-the-art visual perception models for a wide range of tasks rely...
05/02/2018 ∙ by Dhruv Mahajan, et al. ∙ 0 ∙ share

read it
Group Normalization

Batch Normalization (BN) is a milestone technique in the development of ...
03/22/2018 ∙ by Yuxin Wu, et al. ∙ 4 ∙ share

read it
Panoptic Segmentation

We propose and study a novel 'Panoptic Segmentation' (PS) task. Panoptic...
01/03/2018 ∙ by Alexander Kirillov, et al. ∙ 0 ∙ share

read it
Data Distillation: Towards Omni-Supervised Learning

We investigate omni-supervised learning, a special regime of semi-superv...
12/12/2017 ∙ by Ilija Radosavovic, et al. ∙ 0 ∙ share

read it
Learning to Segment Every Thing

Existing methods for object instance segmentation require all training i...
11/28/2017 ∙ by Ronghang Hu, et al. ∙ 0 ∙ share

read it
Non-local Neural Networks

Both convolutional and recurrent operations are building blocks that pro...
11/21/2017 ∙ by Xiaolong Wang, et al. ∙ 0 ∙ share

read it
Transitive Invariance for Self-supervised Visual Representation Learning

Learning visual representations with self-supervised learning has become...
08/09/2017 ∙ by Xiaolong Wang, et al. ∙ 0 ∙ share

read it
Focal Loss for Dense Object Detection

The highest accuracy object detectors to date are based on a two-stage a...
08/07/2017 ∙ by Tsung-Yi Lin, et al. ∙ 0 ∙ share

read it
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Deep learning thrives with large neural networks and large datasets. How...
06/08/2017 ∙ by Priya Goyal, et al. ∙ 0 ∙ share

read it
Mask R-CNN

We present a conceptually simple, flexible, and general framework for ob...
03/20/2017 ∙ by Kaiming He, et al. ∙ 0 ∙ share

read it
Feature Pyramid Networks for Object Detection

Feature pyramids are a basic component in recognition systems for detect...
12/09/2016 ∙ by Tsung-Yi Lin, et al. ∙ 0 ∙ share

read it
Aggregated Residual Transformations for Deep Neural Networks

We present a simple, highly modularized network architecture for image c...
11/16/2016 ∙ by Saining Xie, et al. ∙ 0 ∙ share

read it
R-FCN: Object Detection via Region-based Fully Convolutional Networks

We present region-based, fully convolutional networks for accurate and e...
05/20/2016 ∙ by Jifeng Dai, et al. ∙ 0 ∙ share

read it
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Large-scale data is of crucial importance for learning semantic segmenta...
04/18/2016 ∙ by Di Lin, et al. ∙ 0 ∙ share

read it
Instance-sensitive Fully Convolutional Networks

Fully convolutional networks (FCNs) have been proven very successful for...
03/29/2016 ∙ by Jifeng Dai, et al. ∙ 0 ∙ share

read it
Identity Mappings in Deep Residual Networks

Deep residual networks have emerged as a family of extremely deep archit...
03/16/2016 ∙ by Kaiming He, et al. ∙ 0 ∙ share

read it
Instance-aware Semantic Segmentation via Multi-task Network Cascades

Semantic segmentation research has recently witnessed rapid progress, bu...
12/14/2015 ∙ by Jifeng Dai, et al. ∙ 0 ∙ share

read it
Deep Residual Learning for Image Recognition

Deeper neural networks are more difficult to train. We present a residua...
12/10/2015 ∙ by Kaiming He, et al. ∙ 0 ∙ share

read it
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

State-of-the-art object detection networks depend on region proposal alg...
06/04/2015 ∙ by Shaoqing Ren, et al. ∙ 0 ∙ share

read it
Accelerating Very Deep Convolutional Networks for Classification and Detection

This paper aims to accelerate the test-time computation of convolutional...
05/26/2015 ∙ by Xiangyu Zhang, et al. ∙ 0 ∙ share

read it
Fast Guided Filter

The guided filter is a technique for edge-aware image filtering. Because...
05/05/2015 ∙ by Kaiming He, et al. ∙ 0 ∙ share

read it
Object Detection Networks on Convolutional Feature Maps

Most object detectors contain two important components: a feature extrac...
04/23/2015 ∙ by Shaoqing Ren, et al. ∙ 0 ∙ share

read it
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Recent leading approaches to semantic segmentation rely on deep convolut...
03/05/2015 ∙ by Jifeng Dai, et al. ∙ 0 ∙ share

read it
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Rectified activation units (rectifiers) are essential for state-of-the-a...
02/06/2015 ∙ by Kaiming He, et al. ∙ 0 ∙ share

read it
Image Super-Resolution Using Deep Convolutional Networks

We propose a deep learning method for single image super-resolution (SR)...
12/31/2014 ∙ by Chao Dong, et al. ∙ 0 ∙ share

read it
Convolutional Neural Networks at Constrained Time Cost

Though recent advanced convolutional neural networks (CNNs) have been im...
12/04/2014 ∙ by Kaiming He, et al. ∙ 0 ∙ share

read it
Convolutional Feature Masking for Joint Object and Stuff Segmentation

The topic of semantic segmentation has witnessed considerable progress d...
12/03/2014 ∙ by Jifeng Dai, et al. ∙ 0 ∙ share

read it
Efficient and Accurate Approximations of Nonlinear Convolutional Networks

This paper aims to accelerate the test-time computation of deep convolut...
11/16/2014 ∙ by Xiangyu Zhang, et al. ∙ 0 ∙ share

read it
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Existing deep convolutional neural networks (CNNs) require a fixed-size ...
06/18/2014 ∙ by Kaiming He, et al. ∙ 0 ∙ share

read it

Kaiming He

Featured Co-authors