Search Results for author: Siddarth Asokan

Found 6 papers, 2 papers with code

CROSS-JEM: Accurate and Efficient Cross-encoders for Short-text Ranking Tasks

no code implementations15 Sep 2024 Bhawna Paliwal, Deepak Saini, Mudit Dhawan, Siddarth Asokan, Nagarajan Natarajan, Surbhi Aggarwal, Pankaj Malhotra, Jian Jiao, Manik Varma

In response, we propose Cross-encoders with Joint Efficient Modeling (CROSS-JEM), a novel ranking approach that enables transformer-based models to jointly score multiple items for a query, maximizing parameter utilization.

GANs Settle Scores!

no code implementations2 Jun 2023 Siddarth Asokan, Nishanth Shetty, Aadithya Srikanth, Chandra Sekhar Seelamantula

Generative adversarial networks (GANs) comprise a generator, trained to learn the underlying distribution of the desired data, and a discriminator, trained to distinguish real samples from those output by the generator.

Data Interpolants -- That's What Discriminators in Higher-order Gradient-regularized GANs Are

no code implementations1 Jun 2023 Siddarth Asokan, Chandra Sekhar Seelamantula

We show analytically, via the least-squares (LSGAN) and Wasserstein (WGAN) GAN variants, that the discriminator optimization problem is one of interpolation in $n$-dimensions.

Decoder

Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training

2 code implementations CVPR 2023 Siddarth Asokan, Chandra Sekhar Seelamantula

We demonstrate the efficacy of the Spider approach on DCGAN, conditional GAN, PGGAN, StyleGAN2 and StyleGAN3.

Transfer Learning

Teaching a GAN What Not to Learn

1 code implementation NeurIPS 2020 Siddarth Asokan, Chandra Sekhar Seelamantula

Generative adversarial networks (GANs) were originally envisioned as unsupervised generative models that learn to follow a target distribution.

Philosophy

Cannot find the paper you are looking for? You can Submit a new open access paper.