Search Results for author: Shaunak Halbe

Found 2 papers, 1 papers with code

DAIR: Data Augmented Invariant Regularization

1 code implementation21 Oct 2021 Tianjian Huang, Shaunak Halbe, Chinnadhurai Sankar, Pooyan Amini, Satwik Kottur, Alborz Geramifard, Meisam Razaviyayn, Ahmad Beirami

Synthetic data augmentation followed by empirical risk minimization (DA-ERM) is a simple and widely used solution to remedy this problem.

Data Augmentation Question Answering +1

Exploring Weaknesses of VQA Models through Attribution Driven Insights

no code implementations WS 2020 Shaunak Halbe

Deep Neural Networks have been successfully used for the task of Visual Question Answering for the past few years owing to the availability of relevant large scale datasets.

Question Answering Visual Question Answering +1

Cannot find the paper you are looking for? You can Submit a new open access paper.