R
Ross Girshick
Researcher at Facebook
Publications - 170
Citations - 336844
Ross Girshick is an academic researcher from Facebook. The author has contributed to research in topics: Object detection & Convolutional neural network. The author has an hindex of 97, co-authored 166 publications receiving 231744 citations. Previous affiliations of Ross Girshick include University of Washington & Carnegie Mellon University.
Papers
More filters
Proceedings ArticleDOI
Understanding Objects in Detail with Fine-Grained Attributes
Andrea Vedaldi,Siddharth Mahendran,Stavros Tsogkas,Subhransu Maji,Ross Girshick,Juho Kannala,Esa Rahtu,Iasonas Kokkinos,Matthew B. Blaschko,David J. Weiss,Ben Taskar,Karen Simonyan,Naomi Saphra,Sammy Mohamed +13 more
TL;DR: A dataset of 7, 413 airplanes annotated in detail with parts and their attributes is introduced, leveraging images donated by airplane spotters and crowd-sourcing both the design and collection of the detailed annotations to provide insights that should help researchers interested in designing fine-grained datasets for other basic level categories.
Proceedings Article
On learning to localize objects with minimal supervision
TL;DR: In this article, a discriminative submodular cover problem is used for automatically discovering a set of positive object windows with a smoothed latent SVM formulation, which leverages efficient quasi-Newton optimization techniques.
Patent
Object detection and classification in images
TL;DR: In this article, a computing device can receive an input image and generate a convolutional feature map, which can then be processed through a Region Proposal Network (RPN) to generate proposals for candidate objects in the image.
Posted Content
Analyzing the Performance of Multilayer Neural Networks for Object Recognition
TL;DR: In this paper, the authors experimentally probe several aspects of CNN feature learning in an attempt to help practitioners gain useful, evidence-backed intuitions about how to apply CNNs to computer vision problems.
Posted Content
Designing Network Design Spaces
TL;DR: In this paper, the authors propose a new network design paradigm called RegNet, where instead of focusing on designing individual network instances, they design network design spaces that parametrize populations of networks.