Research
My research interests lie at the intersection of computer vision and machine learning. One of the areas that fascinates me the most is the use of unsupervised and self-supervised learning to alleviate the need for large-scale annotation of training data.
Application of Deep Learning in Facial Recognition
- August 2021
- Chapter published in Design of Intelligent Applications using ML/DL
- An analysis of the modern deep learning models used for the task of face recognition and their strengths/drawbacks
Image Modification using Text with GANs
- Undergraduate research project from August 2019 - May 2020
- The paper can be found here and the code with demos can be found here
- Studied strengths of over 3 approaches for manipulation of image features through natural language descriptions
- Implemented a novel method to change image features such as object colour and shape
- Leveraged PyTorch to train a GAN model on the Caltech-UCSD Birds 200 dataset to change features of bird images
- Extended the technique for virtual trial of clothes by using the DeepFashion dataset