Pawan Kumar Sahu — accepted AI-conference papers

2023

DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks

Samyak Jain, Sravanti Addepalli, Pawan Kumar Sahu, Priyam Dey, R. Venkatesh Babu

CVPR 2023poster

Generalization of Neural Networks is crucial for deploying them safely in the real world. Common training strategies to improve generalization involve the use of data augmentations, ensembling and model averaging. In this work, we first establish a surprisingly simple but strong benchmark for genera…

Cited by 24 Source ↗PDF ↗code ↗Scholar ↗

2023

On Designing Light-Weight Object Trackers Through Network Pruning: Use CNNS or Transformers?

Saksham Aggarwal, Taneesh Gupta, Pawan Kumar Sahu, Arnav Chavan, Rishabh Tiwari, Dilip K. Prasad +1

ICASSP 2023accepted

Object trackers deployed on low-power devices need to be light-weight, however, most of the current state-of-the-art (SOTA) methods rely on using compute-heavy backbones built using CNNs or Transformers. Large sizes of such models do not allow their deployment in low-power conditions and designing c…

Cited by 0 Source ↗Scholar ↗