Vision

This project explores the case for potential bias in generative models such as variational autoencoders. The project also briefly looks at ways to mitigate such bias.

Exploring potential use cases of variational autoencoders in the context of robustness of ML systems.

The project explores CNN classification models and their vulnerability to various adversarial attacks. Also explores a defence mechanism for it.

This project explores personalization of generating image captions. We explore different architecture choices of Attend2u and also analyze personalization of the captions.