K
Kaiming He
Researcher at Facebook
Publications - 140
Citations - 440003
Kaiming He is an academic researcher from Facebook. The author has contributed to research in topics: Object detection & Image segmentation. The author has an hindex of 89, co-authored 135 publications receiving 272091 citations. Previous affiliations of Kaiming He include The Chinese University of Hong Kong & Microsoft.
Papers
More filters
Journal ArticleDOI
Accelerating Very Deep Convolutional Networks for Classification and Detection
TL;DR: This paper aims to accelerate the test-time computation of convolutional neural networks, especially very deep CNNs, and develops an effective solution to the resulting nonlinear optimization problem without the need of stochastic gradient descent (SGD).
Posted Content
Instance-aware Semantic Segmentation via Multi-task Network Cascades
Jifeng Dai,Kaiming He,Jian Sun +2 more
TL;DR: In this article, a multi-task network cascaded structure is proposed for instance-aware semantic segmentation, which consists of three networks, respectively differentiating instances, estimating masks, and categorizing objects.
Proceedings ArticleDOI
Exploring Simple Siamese Representation Learning
Xinlei Chen,Kaiming He +1 more
TL;DR: SimSiam as discussed by the authors proposes to use a stop-gradient operation to prevent collapsing solutions in Siamese networks, which achieves competitive results on ImageNet and downstream tasks, and further shows proof-of-concept experiments verifying it.
Proceedings ArticleDOI
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
TL;DR: Zhang et al. as discussed by the authors proposed to use scribbles to annotate images, and developed an algorithm to train convolutional networks for semantic segmentation supervised by scribbles.
Proceedings ArticleDOI
Feature Denoising for Improving Adversarial Robustness
TL;DR: It is suggested that adversarial perturbations on images lead to noise in the features constructed by these networks, and new network architectures are developed that increase adversarial robustness by performing feature denoising.