63 citations
- Indian Institute of Science BangaloreIN6 papers
- Carnegie Mellon UniversityUS3 papers
- Indian Institute of Technology MadrasIN3 papers
- Karlsruhe Institute of TechnologyDE2 papers
- Robert Bosch (Netherlands)NL2 papers
- University of TübingenDE2 papers
- Arizona State UniversityUS1 paper
- Australian National UniversityAU1 paper
- Carl von Ossietzky Universität OldenburgDE1 paper
- Chemnitz University of TechnologyDE1 paper
- ETH ZurichCH1 paper
- Indian Institute of Technology KharagpurIN1 paper
7 papers · 1 filter
Multi-Instance Aware Localization for End-to-End Imitation Learning
Sagar Gubbi Venkatesh, Raviteja Upadrashta, Shishir Kolathaya +1
Existing architectures for imitation learning using image-to-action policy networks perform poorly when presented with an input image containing multiple instances of the object of…
Imitation Learning for High Precision Peg-in-Hole Tasks
Sagar Gubbi, Shishir Kolathaya, Bharadwaj Amrutur
Industrial robot manipulators are not able to match the precision and speed with which humans are able to execute contact rich tasks even to this day. Therefore, as a means overcom…
Teaching Robots Novel Objects by Pointing at Them
Sagar Gubbi Venkatesh, Raviteja Upadrashta, Shishir Kolathaya +1
Robots that must operate in novel environments and collaborate with humans must be capable of acquiring new knowledge from human experts during operation. We propose teaching a rob…
Convergence Analysis of Homotopy-SGD for non-convex optimization
Matilde Gargiani, Andrea Zanelli, Quoc Tran-Dinh +2
First-order stochastic methods for solving large-scale non-convex optimization problems are widely used in many big-data applications, e.g. training deep neural networks as well as…
Unsupervised Video Representation Learning by Bidirectional Feature Prediction
Nadine Behrmann, Juergen Gall, Mehdi Noroozi
This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature pred…
Adversarial and Natural Perturbations for General Robustness
Sadaf Gulshad, Jan Hendrik Metzen, Arnold Smeulders
In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which…