Search Results for author: Kaiming He

Found 57 papers, 42 papers with code

An Empirical Study of Training Self-Supervised Vision Transformers

2 code implementations5 Apr 2021 Xinlei Chen, Saining Xie, Kaiming He

In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT.

Self-Supervised Image Classification Self-Supervised Learning

Exploring Simple Siamese Representation Learning

15 code implementations CVPR 2021 Xinlei Chen, Kaiming He

Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing.

Self-Supervised Image Classification Unsupervised Representation Learning

Graph Structure of Neural Networks

2 code implementations ICML 2020 Jiaxuan You, Jure Leskovec, Kaiming He, Saining Xie

Neural networks are often represented as graphs of connections between neurons.

Are Labels Necessary for Neural Architecture Search?

2 code implementations ECCV 2020 Chenxi Liu, Piotr Dollár, Kaiming He, Ross Girshick, Alan Yuille, Saining Xie

Existing neural network architectures in computer vision -- whether designed by humans or by machines -- were typically found using both images and their associated labels.

Neural Architecture Search

Improved Baselines with Momentum Contrastive Learning

21 code implementations9 Mar 2020 Xinlei Chen, Haoqi Fan, Ross Girshick, Kaiming He

Contrastive unsupervised learning has recently shown encouraging progress, e. g., in Momentum Contrast (MoCo) and SimCLR.

Contrastive Learning Data Augmentation +3

A Multigrid Method for Efficiently Training Video Models

3 code implementations CVPR 2020 Chao-yuan Wu, Ross Girshick, Kaiming He, Christoph Feichtenhofer, Philipp Krähenbühl

We empirically demonstrate a general and robust grid schedule that yields a significant out-of-the-box training speedup without a loss in accuracy for different models (I3D, non-local, SlowFast), datasets (Kinetics, Something-Something, Charades), and training settings (with and without pre-training, 128 GPUs or 1 GPU).

Action Detection Action Recognition +1

TensorMask: A Foundation for Dense Object Segmentation

2 code implementations ICCV 2019 Xinlei Chen, Ross Girshick, Kaiming He, Piotr Dollár

To formalize this, we treat dense instance segmentation as a prediction task over 4D tensors and present a general framework called TensorMask that explicitly captures this geometry and enables novel operators on 4D tensors.

Instance Segmentation Object Detection +1

Panoptic Feature Pyramid Networks

9 code implementations CVPR 2019 Alexander Kirillov, Ross Girshick, Kaiming He, Piotr Dollár

In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks.

Instance Segmentation Panoptic Segmentation

GLoMo: Unsupervised Learning of Transferable Relational Graphs

no code implementations NeurIPS 2018 Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He, William W. Cohen, Ruslan R. Salakhutdinov, Yann Lecun

We also show that the learned graphs are generic enough to be transferred to different embeddings on which the graphs have not been trained (including GloVe embeddings, ELMo embeddings, and task-specific RNN hidden units), or embedding-free units such as image pixels.

Image Classification Natural Language Inference +4

Rethinking ImageNet Pre-training

1 code implementation ICCV 2019 Kaiming He, Ross Girshick, Piotr Dollár

We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization.

Instance Segmentation Object Detection +1

GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations

1 code implementation14 Jun 2018 Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He, William W. Cohen, Ruslan Salakhutdinov, Yann Lecun

We also show that the learned graphs are generic enough to be transferred to different embeddings on which the graphs have not been trained (including GloVe embeddings, ELMo embeddings, and task-specific RNN hidden unit), or embedding-free units such as image pixels.

Image Classification Natural Language Inference +4

Group Normalization

18 code implementations ECCV 2018 Yuxin Wu, Kaiming He

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Object Detection Video Classification

Data Distillation: Towards Omni-Supervised Learning

4 code implementations CVPR 2018 Ilija Radosavovic, Piotr Dollár, Ross Girshick, Georgia Gkioxari, Kaiming He

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data.

Keypoint Detection Object Detection

Learning to Segment Every Thing

3 code implementations CVPR 2018 Ronghang Hu, Piotr Dollár, Kaiming He, Trevor Darrell, Ross Girshick

Most methods for object instance segmentation require all training examples to be labeled with segmentation masks.

Instance Segmentation Semantic Segmentation

Non-local Neural Networks

22 code implementations CVPR 2018 Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.

Ranked #7 on Action Classification on Toyota Smarthome dataset (using extra training data)

Action Classification Action Recognition +3

Transitive Invariance for Self-supervised Visual Representation Learning

no code implementations ICCV 2017 Xiaolong Wang, Kaiming He, Abhinav Gupta

The objects are connected by two types of edges which correspond to two types of invariance: "different instances but a similar viewpoint and category" and "different viewpoints of the same instance".

Multi-Task Learning Object Detection +2

Focal Loss for Dense Object Detection

207 code implementations ICCV 2017 Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollár

Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.

Dense Object Detection Long-tail Learning +2

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

50 code implementations8 Jun 2017 Priya Goyal, Piotr Dollár, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, Kaiming He

To achieve this result, we adopt a hyper-parameter-free linear scaling rule for adjusting learning rates as a function of minibatch size and develop a new warmup scheme that overcomes optimization challenges early in training.

Stochastic Optimization

Detecting and Recognizing Human-Object Interactions

2 code implementations CVPR 2018 Georgia Gkioxari, Ross Girshick, Piotr Dollár, Kaiming He

Our hypothesis is that the appearance of a person -- their pose, clothing, action -- is a powerful cue for localizing the objects they are interacting with.

Human-Object Interaction Detection

Mask R-CNN

136 code implementations ICCV 2017 Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick

Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.

3D Instance Segmentation Human Part Segmentation +7

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

44 code implementations NeurIPS 2016 Jifeng Dai, Yi Li, Kaiming He, Jian Sun

In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.

Real-Time Object Detection

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

no code implementations CVPR 2016 Di Lin, Jifeng Dai, Jiaya Jia, Kaiming He, Jian Sun

Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure.

Semantic Segmentation

Instance-sensitive Fully Convolutional Networks

no code implementations29 Mar 2016 Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, Jian Sun

In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances.

Semantic Segmentation

Identity Mappings in Deep Residual Networks

46 code implementations16 Mar 2016 Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors.

Image Classification

Deep Residual Learning for Image Recognition

332 code implementations CVPR 2016 Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Breast Tumour Classification Domain Generalization +8

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

155 code implementations NeurIPS 2015 Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun

In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.

Real-Time Object Detection Region Proposal

A Geodesic-Preserving Method for Image Warping

no code implementations CVPR 2015 Dongping Li, Kaiming He, Jian Sun, Kun Zhou

The image projections will turn the straight lines into curved "geodesic lines", and it is fundamentally impossible to keep all these lines straight.

Image Manipulation

Accelerating Very Deep Convolutional Networks for Classification and Detection

no code implementations26 May 2015 Xiangyu Zhang, Jianhua Zou, Kaiming He, Jian Sun

This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs that have substantially impacted the computer vision community.

Classification General Classification +2

Fast Guided Filter

5 code implementations5 May 2015 Kaiming He, Jian Sun

The guided filter is a technique for edge-aware image filtering.

Object Detection Networks on Convolutional Feature Maps

no code implementations23 Apr 2015 Shaoqing Ren, Kaiming He, Ross Girshick, Xiangyu Zhang, Jian Sun

We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier.

General Classification Image Classification +2

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

no code implementations ICCV 2015 Jifeng Dai, Kaiming He, Jian Sun

Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks.

Semantic Segmentation

Image Super-Resolution Using Deep Convolutional Networks

49 code implementations31 Dec 2014 Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang

We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.

Image Super-Resolution Video Super-Resolution

Convolutional Neural Networks at Constrained Time Cost

no code implementations CVPR 2015 Kaiming He, Jian Sun

Though recent advanced convolutional neural networks (CNNs) have been improving the image recognition accuracy, the models are getting more complex and time-consuming.

Convolutional Feature Masking for Joint Object and Stuff Segmentation

1 code implementation CVPR 2015 Jifeng Dai, Kaiming He, Jian Sun

The current leading approaches for semantic segmentation exploit shape information by extracting CNN features from masked image regions.

Semantic Segmentation

Efficient and Accurate Approximations of Nonlinear Convolutional Networks

no code implementations CVPR 2015 Xiangyu Zhang, Jianhua Zou, Xiang Ming, Kaiming He, Jian Sun

This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs).

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

11 code implementations18 Jun 2014 Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale.

General Classification Image Classification +2

Product Sparse Coding

no code implementations CVPR 2014 Tiezheng Ge, Kaiming He, Jian Sun

In this paper, we study a special case of sparse coding in which the codebook is a Cartesian product of two subcodebooks.

General Classification Image Classification +1

Optimized Product Quantization for Approximate Nearest Neighbor Search

no code implementations CVPR 2013 Tiezheng Ge, Kaiming He, Qifa Ke, Jian Sun

Product quantization is an effective vector quantization approach to compactly encode high-dimensional vectors for fast approximate nearest neighbor (ANN) search.


K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes

no code implementations CVPR 2013 Kaiming He, Fang Wen, Jian Sun

We propose a novel Affinity-Preserving K-means algorithm which simultaneously performs k-means clustering and learns the binary indices of the quantized cells.


Cannot find the paper you are looking for? You can Submit a new open access paper.