K
Ke Li
Researcher at Simon Fraser University
Publications - 109
Citations - 4494
Ke Li is an academic researcher from Simon Fraser University. The author has contributed to research in topics: Deep learning & Convolutional neural network. The author has an hindex of 24, co-authored 105 publications receiving 2687 citations. Previous affiliations of Ke Li include University of California & Peking University.
Papers
More filters
Journal ArticleDOI
Object detection in optical remote sensing images: A survey and a new benchmark
TL;DR: A comprehensive review of the recent deep learning based object detection progress in both the computer vision and earth observation communities is provided and a large-scale, publicly available benchmark for object DetectIon in Optical Remote sensing images is proposed, which is named as DIOR.
Journal ArticleDOI
Low-dose CT via convolutional neural network
TL;DR: A deep convolutional neural network is here used to map low-dose CT images towards its corresponding normal-dose counterparts in a patch-by-patch fashion, demonstrating a great potential of the proposed method on artifact reduction and structure preservation.
Journal ArticleDOI
Rotation-Insensitive and Context-Augmented Object Detection in Remote Sensing Images
TL;DR: This paper proposes a novel deep-learning-based object detection framework including region proposal network (RPN) and local-contextual feature fusion network designed for remote sensing images that can deal with the multiangle and multiscale characteristics of geospatial objects.
Posted Content
Learning to Optimize
Ke Li,Jitendra Malik +1 more
TL;DR: In this article, a reinforcement learning approach is used to learn an optimization algorithm using guided policy search and demonstrate that the resulting algorithm outperforms existing hand-engineered algorithms in terms of convergence speed and/or the final objective value.
Proceedings Article
Learning to Optimize.
Ke Li,Jitendra Malik +1 more
TL;DR: In this paper, a reinforcement learning approach is used to learn an optimization algorithm using guided policy search and demonstrate that the resulting algorithm outperforms existing hand-engineered algorithms in terms of convergence speed and/or the final objective value.