Search Results for author: Prathosh AP

Found 15 papers, 5 papers with code

Reweighing auxiliary losses in supervised learning

no code implementations7 Feb 2022 Durga Sivasubramanian, Ayush Maheshwari, Pradeep Shenoy, Prathosh AP, Ganesh Ramakrishnan

Auxiliary losses are introduced here to combat labelling functions that may be noisy rule-based approximations of true labels.

Denoising Knowledge Distillation +1

ScRAE: Deterministic Regularized Autoencoders with Flexible Priors for Clustering Single-cell Gene Expression Data

1 code implementation16 Jul 2021 Arnab Kumar Mondal, Himanshu Asnani, Parag Singla, Prathosh AP

The basic idea in RAEs is to learn a non-linear mapping from the high-dimensional data space to a low-dimensional latent space and vice-versa, simultaneously imposing a distributional prior on the latent space, which brings in a regularization effect.

Generalization on Unseen Domains via Inference-Time Label-Preserving Target Projections

no code implementations CVPR 2021 Prashant Pandey, Mrigank Raman, Sumanth Varambally, Prathosh AP

Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem.

Domain Generalization

Domain Generalization via Inference-time Label-Preserving Target Projections

no code implementations1 Mar 2021 Prashant Pandey, Mrigank Raman, Sumanth Varambally, Prathosh AP

Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem.

Domain Generalization

A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition

no code implementations3 Oct 2020 Ayush Srivastava, Oshin Dutta, Prathosh AP, Sumeet Agarwal, Jigyasa Gupta

In the last few years, compression of deep neural networks has become an important strand of machine learning and computer vision research.

Action Recognition

Discrepancy Minimization in Domain Generalization with Generative Nearest Neighbors

no code implementations28 Jul 2020 Prashant Pandey, Mrigank Raman, Sumanth Varambally, Prathosh AP

Features extracted from this source domain are learned using a generative model whose latent space is used as a sampler to retrieve the nearest neighbors for the target data points.

Domain Generalization

Unsupervised Domain Adaptation for Semantic Segmentation of NIR Images through Generative Latent Search

2 code implementations ECCV 2020 Prashant Pandey, Aayush Kumar Tyagi, Sameer Ambekar, Prathosh AP

Therefore we cast the skin segmentation problem as that of target-independent Unsupervised Domain Adaptation (UDA) where we use the data from the Red-channel of the visible-range to develop skin segmentation algorithm on NIR images.

Semantic Segmentation Unsupervised Domain Adaptation

To Regularize or Not To Regularize? The Bias Variance Trade-off in Regularized AEs

no code implementations10 Jun 2020 Arnab Kumar Mondal, Himanshu Asnani, Parag Singla, Prathosh AP

Specifically, we consider the class of RAEs with deterministic Encoder-Decoder pairs, Wasserstein Auto-Encoders (WAE), and show that having a fixed prior distribution, \textit{a priori}, oblivious to the dimensionality of the `true' latent space, will lead to the infeasibility of the optimization problem considered.

C-MI-GAN : Estimation of Conditional Mutual Information using MinMax formulation

no code implementations17 May 2020 Arnab Kumar Mondal, Arnab Bhattacharya, Sudipto Mukherjee, Prathosh AP, Sreeram Kannan, Himanshu Asnani

Estimation of information theoretic quantities such as mutual information and its conditional variant has drawn interest in recent times owing to their multifaceted applications.

Target-Independent Domain Adaptation for WBC Classification using Generative Latent Search

1 code implementation11 May 2020 Prashant Pandey, Prathosh AP, Vinay Kyatham, Deepak Mishra, Tathagato Rai Dastidar

We prove the existence of such a clone given that infinite number of data points can be sampled from the source distribution.

MaskAAE: Latent space optimization for Adversarial Auto-Encoders

no code implementations10 Dec 2019 Arnab Kumar Mondal, Sankalan Pal Chowdhury, Aravind Jayendran, Parag Singla, Himanshu Asnani, Prathosh AP

The field of neural generative models is dominated by the highly successful Generative Adversarial Networks (GANs) despite their challenges, such as training instability and mode collapse.

Guided Weak Supervision for Action Recognition with Scarce Data to Assess Skills of Children with Autism

1 code implementation11 Nov 2019 Prashant Pandey, Prathosh AP, Manu Kohli, Josh Pritchard

In this paper, we propose to automate the response measurement through video recording of the scene following the use of Deep Neural models for human action recognition from videos.

Action Recognition

Variational Inference with Latent Space Quantization for Adversarial Resilience

1 code implementation24 Mar 2019 Vinay Kyatham, Mayank Mishra, Tarun Kumar Yadav, Deepak Mishra, Prathosh AP

Specifically, we simultaneously auto-encode the data manifold and its perturbations implicitly through the perturbations of the regularized and quantized generative latent space, realized using variational inference.

Quantization Variational Inference

Unsupervised Conditional Generation using noise engineered mode matching GAN

no code implementations27 Sep 2018 Deepak Mishra, Prathosh AP, Aravind J, Prashant Pandey, Santanu Chaudhury

Conditional generation refers to the process of sampling from an unknown distribution conditioned on semantics of the data.

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