12 citations · 19 across the 5 of their papers we have counts for
6 papers
Generalizable Pose Estimation Using Implicit Scene Representations
Vaibhav Saxena, Kamal Rahimi Malekshan, Linh Tran +1
6-DoF pose estimation is an essential component of robotic manipulation pipelines. However, it usually suffers from a lack of generalization to new instances and object types. Most…
Clockwork Variational Autoencoders
Vaibhav Saxena, Jimmy Ba, Danijar Hafner
Deep learning has enabled algorithms to generate realistic images. However, accurately predicting long video sequences requires understanding long-term dependencies and remains an…
Effective Elastic Scaling of Deep Learning Workloads
Vaibhav Saxena, K. R. Jayaram, Saurav Basu +2
The increased use of deep learning (DL) in academia, government and industry has, in turn, led to the popularity of on-premise and cloud-hosted deep learning platforms, whose goals…
Dyna-AIL : Adversarial Imitation Learning by Planning
Vaibhav Saxena, Srinivasan Sivanandan, Pulkit Mathur
Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergenc…
Efficient Training of Convolutional Neural Nets on Large Distributed Systems
Sameer Kumar, Dheeraj Sreedhar, Vaibhav Saxena +2
Deep Neural Networks (DNNs) have achieved im- pressive accuracy in many application domains including im- age classification. Training of DNNs is an extremely compute- intensive pr…
PowerAI DDL
Minsik Cho, Ulrich Finkler, Sameer Kumar +3
As deep neural networks become more complex and input datasets grow larger, it can take days or even weeks to train a deep neural network to the desired accuracy. Therefore, distri…