Posts by Collection

portfolio

projects

Autonomous Object Detection

Published:

This project initially started as a code base for this hackathon. This is a winning entry (team B) on the leaderboard. It later was transformed into a common project for object detection for autonomous driving. It later was also used for ICCVW 2019 (AutoNUE) paper. The code is publicly available at this Github URL. Read more

publications

Adaptive Transformers for Learning Multimodal Representations

Published in ACL SRW, 2020

Abstract

The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we extend adaptive approaches to learn more about model interpretability and computational efficiency. Specifically, we study attention spans, sparse, and structured dropout methods to help understand how their attention mechanism extends for vision and language tasks. We further show that these approaches can help us learn more about how the network perceives the complexity of input sequences, sparsity preferences for different modalities, and other related phenomena. Read more

talks

Distilling the knowledge in Neural Networks

Published:

This was an invited talk in collaboration with Intel and Analytics Vidhya. I mainly spoke on fundamentals of computer vision, few interesting research ideas and using Intel’s architecture to fasten the process of training neural nets. Read more

teaching