I work as a principal scientist in Deep Learning and Artificial Intelligence Group (DLAI), TCS Research in New Delhi, India. My main focus is on computer vision and trustworthy machine learning. My doctoral research advised by Prof. Chetan Arora at IIT Delhi is centered on proposing novel methods to enhance reliability in deep neural networks (DNNs)
Prior to this, I was fortunate to be working with Prof. Ramakrishna Kakarala at Nanyang Technological University on High Dynamic Range Imaging algorithms which formed a part of the image processing pipeline aimed at smartphone cameras. Our research was recognized with the Best Student Paper award at the 2012 SPIE conference in Burlingame, California. I completed my master's degree at DCUs School of Electronic Engineering and Computing in 2014, advised by Prof. Noel O'Connor and Prof. Alan Smeaton. I focused on reducing false alarms in surveillance camera networks. As a result of this work, a portion of our research was licensed to Netwatch Systems.
In June 2015, I started working as a research scientist at TCS Research. I have also been involved in various projects related to augmented reality. Specifically, I have focused on optimizing the layout of labels for immersive experiences and developing gestural interfaces for head-mounted devices and smartphones. As a team leader, I have overseen the development of a cost-effective industrial inspection framework. Recently, my team has been working on creative content generation (images, videos, 3D/4D data).
We introduce ReMOVE, a novel reference-free metric for assessing object erasure efficacy in diffusion-based image editing models post-generation. Unlike existing measures such as LPIPS and CLIPScore, ReMOVE addresses the challenge of evaluating inpainting without a reference image, common in practical scenarios. ReMOVE effectively distinguishes between object removal and replacement, a key issue in diffusion models due to stochastic nature of image generation.
Transfer4D transfers motion from a commodity depth sensor to a virtual model. The goal of our work is to democratize animation transfer using commodity depth sensors and alleviate the animators effort by automating the rigging and animation transfer process.
We demonstrate state-of-the-art Deep Neural Network calibration performance via proposing a differentiable loss term
that can be used effectively in gradient descent optimisation and dynamic data pruning strategy not only enhances legitimate
high confidence samples to enhance trust in DNN classifiers but also reduce the training time for calibration.
We propose a novel Compounded Corruption(CnC) technique for the Out-of-Distribution data augmentation. One of the major advantages of CnC is that it does not require any hold-out data apart from the training set. Our extensive comparison with 20 methods from the major conferences in last 4 years show that a model trained using CnC based data augmentation, significantly outperforms SOTA, both in terms of OOD detection accuracy as well as inference time.
We propose a novel auxiliary loss function: Multi-class Difference in Confidence and Accuracy (MDCA) for Deep Neural Network calibration. The loss can be combined with any application specific classification losses for image, NLP, Speech domains. We also demonstrate the utility of the loss in semantic segmentation tasks.