Ramya Hebbalaguppe

I work as a research scientist, Deep Learning and Artificial Intelligence Group, TCS Research in New Delhi, India, where 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 for trustworthy/reliable 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. In addition to my work on computer vision and machine learning, 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 developing affordable solutions for motion capture and deformation capture.

> Email  /  Google Scholar  /  Twitter  /  Github

profile photo
Research

I'm interested in visual computing (computer vision, computational photography, and computer graphics) and reliable/robustness in machine learning (out-of-distribution detection, Deep neural network calibration, uncertainty quantification, continual learning). Representative papers are highlighted.

ReMOVE: A Reference-free Metric for Object Erasure
Aditya Chandrasekar, Goirik Chakrabarty, Jai Bardhan, Ramya Hebbalaguppe, Prathosh AP,
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPRW) The First Workshop on the Evaluation of Generative Foundation Models, 2024  
project page

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. It effectively distinguishes between object removal and replacement. This is a key issue in diffusion models due to stochastic nature of image generation. Traditional metrics fail to align with the intuitive definition of inpainting, which aims for (1) seamless object removal within masked regions (2) while preserving the background continuity.

Transfer4D: A framework for frugal motion capture and deformation transfer
Shubh Maheshwari, Rahul Narain, Ramya Hebbalaguppe,
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023  
project page

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.

Calibrating Deep Neural Networks Using Explicit Regularisation and Dynamic Data Pruning
Rishabh Patra*, Ramya Hebbalaguppe*, Tirtharaj Dash, Gautam Shroff, Lovekesh Vig,
IEEE/CVF Winter Conference on Applications of Computer Vision, 2023   -- [Spotlight Presentation]
project page

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.

A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions
Ramya Hebbalaguppe, Soumya Suvra Ghosal, Jatin Prakash, Harshad Khadilkar, Chetan Arora,
European Conference on Machine Learning , 2022  
project page

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.

A stitch in time saves nine: A train-time regularizing loss for improved neural network calibration
Ramya Hebbalaguppe*, Jatin Prakash, Neelabh Madan*, Chetan Arora,
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2022   -- [ORAL Presentation]
project page

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.

Current team at TCS Research, IIT Delhi

Supervised the following full-time researchers/research interns


Website inspired from Jon Barron's.