Sourav Pal

I am a fourth year PhD student of Computer Sciences at UW-Madison. I am very fortunate to be advised by Prof. Vikas Singh. My broad research interests are in Machine Learning and their applications to problems in Computer Vision. I am specifically interested in harmonic analysis and hybrid models which combine strong function approximation properties of neural networks along side differntial equations to model real life physical processes.

Before coming to Madison I was part of Adobe Acrobat Reader team. Even before I was a Research Intern at the BigData Experience Lab of Adobe Research where I worked with an amazing mentor, Dr. Ritwik Sinha.

As an undergrad I spent four beautiful years, at the Indian Institute of Technology (IIT) Kharagpur from where I graduated with a B.Tech (Hons.) in Computer Science and Engineering. I was fortunate enough to be advised by Prof. Pabitra Mitra during my undergraduate studies.

Email  /  Twitter /  GitHub  /  Google Scholar  /  LinkedIn

profile photo
Recent Updates:

June 22: Our work on machine unlearning will also appear at UpML 2022 – Updatable Machine Learning Workshop at ICML

June 22: Research Internship at Microsoft Research in the Computer Vision group working with Dr. Vibhav Vineet and Dr. Neel Joshi

May 22: Our paper on multi resolution analysis for efficient self attention got accepted to ICML 2022

Mar 22: Our paper on machine unlearning got accepted to CVPR 2022

Multi Resolution Analysis (MRA) for Approximate Self-Attention
Zhanpeng Zeng, Sourav Pal, Jeffery Kline, Glenn Fung, Vikas Singh
ICML 2022

We revisit classical Multiresolution Analysis (MRA) concepts such as Wavelets, whose potential value in this setting remains underexplored thus far. We show that simple approximations based on empirical feedback and design choices informed by modern hardware and implementation challenges, eventually yield a MRA-based approach for self-attention with an excellent performance profile across most criteria of interest. We undertake an extensive set of experiments and demonstrate that this multi-resolution scheme outperforms most efficient self-attention proposals and is favorable for both short and long sequences


Deep Unlearning via Randomized Conditionally Independent Hessians
Sourav Pal*, Ronak Mehta*, Vikas Singh, Sathya N. Ravi
CVPR 2022
Also in UpML 2022 – Updatable Machine Learning Workshop at ICML 2022

Machine Unlearning is the art of removing specific training samples from a predictive model as if they never existed in the training dataset. Recent ideas leveraging optimization-based updates scale poorly with the model dimension d, due to inverting the Hessian of the loss function. We use a variant of a new conditional independence coefficient, L-CODEC, to identify a subset of the model parameters with the most semantic overlap on an individual sample level. Our approach completely avoids the need to invert a (possibly) huge matrix. Our approach makes approximate unlearning possible in settings that would otherwise be infeasible, including vision models used for face recognition, person reidentification and transformer based NLP models.


D-FJ: Deep Neural Network Based Factuality Judgment
Ankan Mullick, Sourav Pal, Projjal Chanda, Arijit Panigrahy, Anurag Bharadwaj, Siddhant Singh, Tanmoy Dam
TrueFact, SIGKDD, 2019

Deep neural networks to detect facts and opinions from online news media. We have also shown how factuality, opinionatedness and sentiment fraction of different news articles changes over certain events in different time frames.

Visual Attention for Behavioral Cloning in Autonomous Driving
Sourav Pal*, Tharun Mohandoss*, Pabitra Mitra
ICMV, 2018

We present two methods of predicting visual attention maps. The first method is a supervised learning approach in which we collect eye-gaze data for the task of driving and use this to train a model for predicting the attention map. The second method is a novel unsupervised approach where we train a model to learn to predict attention as it learns to drive a car.

Saliency Prediction for Mobile User Interfaces
Prakhar Gupta, Sourav Pal*, Shubh Gupta* , Ajaykrishnan Jayagopal*, Ritwik Sinha
WACV, 2018

We introduce deep learning models for saliency prediction for mobile user interfaces at the element level to improve their usability.

Saliency Prediction for a Mobile User Interface

Saliency Prediction for Informational Documents

Stack Overflow'ed from here