Kaiming He

SlowFast Networks for Video Recognition

We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, op...

Momentum Contrast for Unsupervised Visual Representation Learning

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic diction...

Non-local Neural Networks

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family...

Focal Loss for Dense Object Detection

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations...

Deep Residual Learning for Image Recognition

Actualmente diversas investigaciones se han enfocado en analizar a partir de videos de alta velocidad, características de las descargas eléctricas atmosféricas con el fin de adq...

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

Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two as...

Identity Mappings in Deep Residual Networks

Image Super-Resolution Using Deep Convolutional Networks

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is...

Panoptic Feature Pyramid Networks

The recently introduced panoptic segmentation task has renewed our community's interest in unifying the tasks of instance segmentation (for thing classes) and semantic segmentat...

Mask R-CNN

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously gen...

Feature Pyramid Networks for Object Detection

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors...

Aggregated Residual Transformations for Deep Neural Networks

We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transfor...