Search Results for author: Arnab Kumar Mondal

Found 13 papers, 5 papers with code

Equivariance with Learned Canonicalization Functions

no code implementations11 Nov 2022 Sékou-Oumar Kaba, Arnab Kumar Mondal, Yan Zhang, Yoshua Bengio, Siamak Ravanbakhsh

Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations.

Transformation Coding: Simple Objectives for Equivariant Representations

no code implementations19 Feb 2022 Mehran Shakerinava, Arnab Kumar Mondal, Siamak Ravanbakhsh

We present a simple non-generative approach to deep representation learning that seeks equivariant deep embedding through simple objectives.

Disentanglement reinforcement-learning +1

Investigating Power laws in Deep Representation Learning

no code implementations11 Feb 2022 Arna Ghosh, Arnab Kumar Mondal, Kumar Krishna Agrawal, Blake Richards

Access to task relevant labels at scale is often scarce or expensive, motivating the need to learn from unlabelled datasets with self-supervised learning (SSL).

Representation Learning Scene Recognition +1

EqR: Equivariant Representations for Data-Efficient Reinforcement Learning

no code implementations29 Sep 2021 Arnab Kumar Mondal, Vineet Jain, Kaleem Siddiqi, Siamak Ravanbakhsh

We study different notions of equivariance as an inductive bias in Reinforcement Learning (RL) and propose new mechanisms for recovering representations that are equivariant to both an agent’s action, and symmetry transformations of the state-action pairs.

Atari Games Inductive Bias +2

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.

Mini-batch graphs for robust image classification

no code implementations22 Apr 2021 Arnab Kumar Mondal, Vineet Jain, Kaleem Siddiqi

Current deep learning models for classification tasks in computer vision are trained using mini-batches.

Classification General Classification +2

RespVAD: Voice Activity Detection via Video-Extracted Respiration Patterns

1 code implementation21 Aug 2020 Arnab Kumar Mondal, Prathosh A. P

The Respiration Pattern is first extracted from the video focusing on the abdominal-thoracic region of a speaker using an optical flow based method.

Action Detection Activity Detection +1

Group Equivariant Deep Reinforcement Learning

1 code implementation1 Jul 2020 Arnab Kumar Mondal, Pratheeksha Nair, Kaleem Siddiqi

In Reinforcement Learning (RL), Convolutional Neural Networks(CNNs) have been successfully applied as function approximators in Deep Q-Learning algorithms, which seek to learn action-value functions and policies in various environments.

Inductive Bias Q-Learning +2

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.

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.

Revisiting CycleGAN for semi-supervised segmentation

1 code implementation30 Aug 2019 Arnab Kumar Mondal, Aniket Agarwal, Jose Dolz, Christian Desrosiers

In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotation efforts.

Image Segmentation Semantic Segmentation +1

Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning

1 code implementation29 Oct 2018 Arnab Kumar Mondal, Jose Dolz, Christian Desrosiers

In addition, our work presents a comprehensive analysis of different GAN architectures for semi-supervised segmentation, showing recent techniques like feature matching to yield a higher performance than conventional adversarial training approaches.

3D Medical Imaging Segmentation Brain Image Segmentation +4

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