D
Dhruv Batra
Researcher at Georgia Institute of Technology
Publications - 272
Citations - 43803
Dhruv Batra is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Question answering & Dialog box. The author has an hindex of 69, co-authored 272 publications receiving 29938 citations. Previous affiliations of Dhruv Batra include Facebook & Toyota Technological Institute at Chicago.
Papers
More filters
Journal ArticleDOI
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Ramprasaath R. Selvaraju,Michael Cogswell,Abhishek Das,Ramakrishna Vedantam,Devi Parikh,Dhruv Batra +5 more
TL;DR: Grad-CAM as discussed by the authors uses the gradients of any target concept, flowing into the final convolutional layer to produce a coarse localization map highlighting important regions in the image for predicting the concept.
Posted Content
Graph R-CNN for Scene Graph Generation
TL;DR: Graph R-CNN as mentioned in this paper proposes a relation proposal network (RePN) that efficiently deals with the quadratic number of potential relations between objects in an image and an attentional graph convolutional network (aGCN) that effectively captures contextual information between objects and relations.
Journal ArticleDOI
A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
Jörg Hendrik Kappes,Bjoern Andres,Fred A. Hamprecht,Christoph Schnörr,Sebastian Nowozin,Dhruv Batra,Sungwoong Kim,Bernhard X. Kausler,Thorben Kröger,Jan Lellmann,Nikos Komodakis,Bogdan Savchynskyy,Carsten Rother +12 more
TL;DR: In this article, the authors present an empirical comparison of 27 state-of-the-art optimization techniques on a corpus of 2453 energy minimization instances from diverse applications in computer vision.
Proceedings Article
Reducing Overfitting in Deep Networks by Decorrelating Representations
TL;DR: DeCov as mentioned in this paper encourages diverse or non-redundant representations in deep neural networks by minimizing the cross-covariance of hidden activations, which leads to significantly reduced overfitting and better generalization.
Proceedings Article
Diverse Beam Search for Improved Description of Complex Scenes
Ashwin K. Vijayakumar,Michael Cogswell,Ramprasaath R. Selvaraju,Qing Sun,Stefan Lee,David J. Crandall,Dhruv Batra +6 more
TL;DR: Diverse Beam Search is proposed, a diversity promoting alternative to BS for approximate inference that produces sequences that are significantly different from each other by incorporating diversity constraints within groups of candidate sequences during decoding; moreover, it achieves this with minimal computational or memory overhead.