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
Posted Content
Low-shot visual object recognition.
Bharath Hariharan,Ross Girshick +1 more
TL;DR: A novel protocol to evaluate low-shot learning on complex images where the learner is permitted to first build a feature representation is presented, leading to a 2x reduction in the amount of training data required at equal accuracy rates on the challenging ImageNet dataset.
Proceedings ArticleDOI
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Mannat Singh,Laura Gustafson,Aaron Adcock,Vinicius de Freitas Reis,Bugra Gedik,Raj Prateek Kosaraju,Dhruv Mahajan,Ross Girshick,Piotr Doll'ar,Laurens van der Maaten +9 more
TL;DR: This paper revisits weakly-supervised pre-training of models using hashtag supervision with modern versions of residual networks and the largest-ever dataset of images and corresponding hashtags to provide a compelling argument for the use of weakly supervised learning in the development of visual recognition systems.
Proceedings ArticleDOI
Learning by Asking Questions
TL;DR: Learning-by-asking (LBA) as discussed by the authors is an interactive learning framework for the development and testing of intelligent visual systems, which has the potential to be more data-efficient than the traditional VQA setting.
From rigid templates to grammars: object detection with structured models
TL;DR: A new discriminative training framework is proposed that directly supports learning models from weakly-labeled examples and is shown how to apply this framework to the problem of learning the parameters of a grammar model.
Posted Content
Inferring 3D Object Pose in RGB-D Images
TL;DR: The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library by first detecting and segmenting object instances in the scene using the approach from Gupta et al.