This project was done for the course 'Natural Language Understanding and Computational Semantics' at NYU CDS in Spring 2018. It aims at increasing the accuracy of VQA models by augmenting the dataset. The paper written as a result can be found here.
This project was done for the course 'Natural Language Understanding and Computational Semantics' at NYU CDS in Spring 2018. It aims at increasing the accuracy of VQA models by augmenting the dataset. The paper written as a result can be found here.