no code implementations • 9 Apr 2024 • Arkaprabha Basu, Kushal Bose, Sankha Subhra Mullick, Anish Chakrabarty, Swagatam Das
Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to the standard of its High-Resolution (HR) counterpart.
1 code implementation • 7 Apr 2022 • Shounak Datta, Sankha Subhra Mullick, Anish Chakrabarty, Swagatam Das
We then use a novel strategy to artificially form new tasks for training by interpolating between the available tasks and their respective interval bounds.
no code implementations • 26 Aug 2020 • Sankha Subhra Mullick, Shounak Datta, Sourish Gunesh Dhekane, Swagatam Das
Indices quantifying the performance of classifiers under class-imbalance, often suffer from distortions depending on the constitution of the test set or the class-specific classification accuracy, creating difficulties in assessing the merit of the classifier.
no code implementations • 24 Apr 2020 • Arka Ghosh, Sankha Subhra Mullick, Shounak Datta, Swagatam Das, Rammohan Mallipeddi, Asit Kr. Das
Constructing adversarial perturbations for deep neural networks is an important direction of research.
1 code implementation • ICCV 2019 • Sankha Subhra Mullick, Shounak Datta, Swagatam Das
We propose a three-player adversarial game between a convex generator, a multi-class classifier network, and a real/fake discriminator to perform oversampling in deep learning systems.
1 code implementation • 22 Dec 2017 • Shounak Datta, Sayak Nag, Sankha Subhra Mullick, Swagatam Das
The diversification (generating slightly varying separating discriminators) of Support Vector Machines (SVMs) for boosting has proven to be a challenge due to the strong learning nature of SVMs.