Kaiming He

46

Papers

6,103

Total Citations

Papers (46)

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

NeurIPS 2016arXiv

Transformers without Normalization

A Decade's Battle on Dataset Bias: Are We There Yet?

Is Noise Conditioning Necessary for Denoising Generative Models?

Convolutional Feature Masking for Joint Object and Stuff Segmentation

Convolutional Neural Networks at Constrained Time Cost

Deep Residual Learning for Image Recognition

Instance-Aware Semantic Segmentation via Multi-Task Network Cascades

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Aggregated Residual Transformations for Deep Neural Networks

Feature Pyramid Networks for Object Detection

Data Distillation: Towards Omni-Supervised Learning

Learning to Segment Every Thing

Non-Local Neural Networks

Detecting and Recognizing Human-Object Interactions

Long-Term Feature Banks for Detailed Video Understanding

Feature Denoising for Improving Adversarial Robustness

Panoptic Feature Pyramid Networks

Panoptic Segmentation

A Multigrid Method for Efficiently Training Video Models

PointRend: Image Segmentation As Rendering

Momentum Contrast for Unsupervised Visual Representation Learning

Designing Network Design Spaces

Exploring Simple Siamese Representation Learning

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

Masked Autoencoders Are Scalable Vision Learners

Scaling Language-Image Pre-Training via Masking

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

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

Transitive Invariance for Self-Supervised Visual Representation Learning

Mask R-CNN

Focal Loss for Dense Object Detection

Exploring Randomly Wired Neural Networks for Image Recognition

Rethinking ImageNet Pre-Training

SlowFast Networks for Video Recognition

Deep Hough Voting for 3D Object Detection in Point Clouds

An Empirical Study of Training Self-Supervised Vision Transformers

Are Labels Necessary for Neural Architecture Search?

Exploring Plain Vision Transformer Backbones for Object Detection

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

TensorMask: A Foundation for Dense Object Segmentation

A Geodesic-Preserving Method for Image Warping

Efficient and Accurate Approximations of Nonlinear Convolutional Networks

Sparse Projections for High-Dimensional Binary Codes

GLoMo: Unsupervised Learning of Transferable Relational Graphs

Masked Autoencoders As Spatiotemporal Learners