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
Proceedings Article
DivMCuts: Faster Training of Structural SVMs with Diverse M-Best Cutting-Planes
TL;DR: It is shown that significant computational savings can be achieved by adding multiple diverse and highly violated constraints at every iteration of the cutting-plane algorithm, and generation of such diverse cuttingplanes involves extracting diverse M-Best solutions from the loss-augmented score of the training instances.
Posted Content
Combining the Best of Graphical Models and ConvNets for Semantic Segmentation
TL;DR: This work presents a two-module approach to semantic segmentation that incorporates Convolutional Networks (CNNs) and Graphical Models, and achieves $52.5\% on the PASCAL 2012 segmentation challenge.
Posted Content
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: An empirical comparison of more than 27 state-of-the-art optimization techniques on a corpus of 2453 energy minimization instances from diverse applications in computer vision suggests that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.
Posted Content
Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles
Stefan Lee,Senthil Purushwalkam,Michael Cogswell,Viresh Ranjan,David J. Crandall,Dhruv Batra +5 more
TL;DR: This article proposed a stochastic gradient descent based approach to minimize the loss with respect to an oracle, which achieves lower oracle error compared to existing methods on a wide range of tasks and deep architectures.
Posted Content
Decentralized Distributed PPO: Solving PointGoal Navigation
Erik Wijmans,Abhishek Kadian,Ari S. Morcos,Stefan Lee,Irfan Essa,Devi Parikh,Manolis Savva,Dhruv Batra +7 more
TL;DR: It is shown that the scene understanding and navigation policies learned can be transferred to other navigation tasks -- the analog of "ImageNet pre-training + task-specific fine-tuning" for embodied AI.