Search Results for author: Vinay P. Namboodiri

Found 60 papers, 15 papers with code

Gradient Based Activations for Accurate Bias-Free Learning

no code implementations17 Feb 2022 Vinod K Kurmi, Rishabh Sharma, Yash Vardhan Sharma, Vinay P. Namboodiri

The main drawback in such a model is that it directly introduces a trade-off with accuracy as the features that the discriminator deems to be sensitive for discrimination of bias could be correlated with classification.

Class Incremental Online Streaming Learning

no code implementations20 Oct 2021 Soumya Banerjee, Vinay Kumar Verma, Toufiq Parag, Maneesh Singh, Vinay P. Namboodiri

We propose a novel approach (CIOSL) for the class-incremental learning in an \emph{online streaming setting} to address these challenges.

class-incremental learning Incremental Learning +1

Attentive Contractive Flow: Improved Contractive Flows with Lipschitz-constrained Self-Attention

no code implementations24 Sep 2021 Avideep Mukherjee, Badri Narayan Patro, Sahil Sidheekh, Maneesh Singh, Vinay P. Namboodiri

Normalizing flows provide an elegant method for obtaining tractable density estimates from distributions by using invertible transformations.

More Parameters? No Thanks!

1 code implementation Findings (ACL) 2021 Zeeshan Khan, Kartheek Akella, Vinay P. Namboodiri, C V Jawahar

We propose a novel adaptation strategy, where we iteratively prune and retrain the redundant parameters of an MNMT to improve bilingual representations while retaining the multilinguality.

Learning Language specific models Machine Translation +1

Prb-GAN: A Probabilistic Framework for GAN Modelling

no code implementations12 Jul 2021 Blessen George, Vinod K. Kurmi, Vinay P. Namboodiri

Generative adversarial networks (GANs) are very popular to generate realistic images, but they often suffer from the training instability issues and the phenomenon of mode loss.

Variational Inference

Exploring Dropout Discriminator for Domain Adaptation

no code implementations9 Jul 2021 Vinod K Kurmi, Venkatesh K Subramanian, Vinay P. Namboodiri

Among the methodologies used, that of adversarial learning is widely applied to solve many deep learning problems along with domain adaptation.

Domain Adaptation

Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation

no code implementations30 Jun 2021 Pratik Mazumder, Pravendra Singh, Vinay P. Namboodiri

Our approach significantly improves their performance and further reduces the model biases in the limited data regime.

Rectification-based Knowledge Retention for Continual Learning

no code implementations CVPR 2021 Pravendra Singh, Pratik Mazumder, Piyush Rai, Vinay P. Namboodiri

Our proposed method uses weight rectifications and affine transformations in order to adapt the model to different tasks that arrive sequentially.

Continual Learning Generalized Zero-Shot Learning +1

RNNP: A Robust Few-Shot Learning Approach

no code implementations22 Nov 2020 Pratik Mazumder, Pravendra Singh, Vinay P. Namboodiri

Our method relies on generating robust prototypes from a set of few examples.

Few-Shot Learning

SHAD3S: A model to Sketch, Shade and Shadow

2 code implementations13 Nov 2020 Raghav B. Venkataramaiyer, Abhishek Joshi, Saisha Narang, Vinay P. Namboodiri

Hatching is a common method used by artists to accentuate the third dimension of a sketch, and to illuminate the scene.

Determinantal Point Process as an alternative to NMS

1 code implementation26 Aug 2020 Samik Some, Mithun Das Gupta, Vinay P. Namboodiri

We present a determinantal point process (DPP) inspired alternative to non-maximum suppression (NMS) which has become an integral step in all state-of-the-art object detection frameworks.

Object Detection

Revisiting Low Resource Status of Indian Languages in Machine Translation

no code implementations11 Aug 2020 Jerin Philip, Shashank Siripragada, Vinay P. Namboodiri, C. V. Jawahar

Through this paper, we provide and analyse an automated framework to obtain such a corpus for Indian language neural machine translation (NMT) systems.

Machine Translation Translation

A Multilingual Parallel Corpora Collection Effort for Indian Languages

2 code implementations LREC 2020 Shashank Siripragada, Jerin Philip, Vinay P. Namboodiri, C. V. Jawahar

We present sentence aligned parallel corpora across 10 Indian Languages - Hindi, Telugu, Tamil, Malayalam, Gujarati, Urdu, Bengali, Oriya, Marathi, Punjabi, and English - many of which are categorized as low resource.

Machine Translation Translation

Learning to Switch CNNs with Model Agnostic Meta Learning for Fine Precision Visual Servoing

no code implementations9 Jul 2020 Prem Raj, Vinay P. Namboodiri, L. Behera

The idea of switching a CNN is due to the fact that the dataset for training a relative camera pose regressor for visual servo control must contain variations in relative pose ranging from a very small scale to eventually a larger scale.

Meta-Learning Pose Estimation +1

Improving Few-Shot Learning using Composite Rotation based Auxiliary Task

no code implementations29 Jun 2020 Pratik Mazumder, Pravendra Singh, Vinay P. Namboodiri

We then simultaneously train for the composite rotation prediction task along with the original classification task, which forces the network to learn high-quality generic features that help improve the few-shot classification performance.

Classification Few-Shot Learning +1

Passive Batch Injection Training Technique: Boosting Network Performance by Injecting Mini-Batches from a different Data Distribution

no code implementations8 Jun 2020 Pravendra Singh, Pratik Mazumder, Vinay P. Namboodiri

Our proposed technique, namely Passive Batch Injection Training Technique (PBITT), even reduces the level of overfitting in networks that already use the standard techniques for reducing overfitting such as $L_2$ regularization and batch normalization, resulting in significant accuracy improvements.

Object Detection

AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings

no code implementations27 May 2020 Pratik Mazumder, Pravendra Singh, Kranti Kumar Parida, Vinay P. Namboodiri

We use the semantic relatedness of text embeddings as a means for zero-shot learning by aligning audio and video embeddings with the corresponding class label text feature space.

Generalized Zero-Shot Learning

Uncertainty based Class Activation Maps for Visual Question Answering

no code implementations23 Jan 2020 Badri N. Patro, Mayank Lunayach, Vinay P. Namboodiri

These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions.

Probabilistic Deep Learning Question Answering +1

Deep Bayesian Network for Visual Question Generation

no code implementations23 Jan 2020 Badri N. Patro, Vinod K. Kurmi, Sandeep Kumar, Vinay P. Namboodiri

This is a Bayesian framework and the results show a remarkable similarity to natural questions as validated by a human study.

Question Generation

Robust Explanations for Visual Question Answering

1 code implementation23 Jan 2020 Badri N. Patro, Shivansh Pate, Vinay P. Namboodiri

Our model explains the answers obtained through a VQA model by providing visual and textual explanations.

Question Answering Visual Question Answering +1

A "Network Pruning Network" Approach to Deep Model Compression

no code implementations15 Jan 2020 Vinay Kumar Verma, Pravendra Singh, Vinay P. Namboodiri, Piyush Rai

The pruner is essentially a multitask deep neural network with binary outputs that help identify the filters from each layer of the original network that do not have any significant contribution to the model and can therefore be pruned.

Knowledge Distillation Model Compression +3

Cooperative Initialization based Deep Neural Network Training

no code implementations5 Jan 2020 Pravendra Singh, Munender Varshney, Vinay P. Namboodiri

In this paper, we have proposed a cooperative initialization for training the deep network using ReLU activation function to improve the network performance.

General Classification

Revisiting Paraphrase Question Generator using Pairwise Discriminator

1 code implementation31 Dec 2019 Badri N. Patro, Dev Chauhan, Vinod K. Kurmi, Vinay P. Namboodiri

One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.

Paraphrase Generation Sentence Embedding +2

Deep Exemplar Networks for VQA and VQG

no code implementations19 Dec 2019 Badri N. Patro, Vinay P. Namboodiri

Specifically, we incorporate exemplar based approaches and show that an exemplar based module can be incorporated in almost any of the deep learning architectures proposed in the literature and the addition of such a block results in improved performance for solving these tasks.

Question Answering Question Generation +2

Jointly Trained Image and Video Generation using Residual Vectors

no code implementations17 Dec 2019 Yatin Dandi, Aniket Das, Soumye Singhal, Vinay P. Namboodiri, Piyush Rai

The proposed model allows minor variations in content across frames while maintaining the temporal dependence through latent vectors encoding the pose or motion features.

Disentanglement Image Generation +1

Can I teach a robot to replicate a line art

no code implementations17 Oct 2019 Raghav Brahmadesam Venkataramaiyer, Subham Kumar, Vinay P. Namboodiri

Line art is arguably one of the fundamental and versatile modes of expression.

Dynamic Attention Networks for Task Oriented Grounding

no code implementations14 Oct 2019 Soumik Dasgupta, Badri N. Patro, Vinay P. Namboodiri

In this work, we show that Dynamic Attention helps in achieving grounding and also aids in the policy learning objective.

Granular Multimodal Attention Networks for Visual Dialog

no code implementations13 Oct 2019 Badri N. Patro, Shivansh Patel, Vinay P. Namboodiri

Particularly, in this work, we propose a new method Granular Multi-modal Attention, where we aim to particularly address the question of the right granularity at which one needs to attend while solving the Visual Dialog task.

Visual Dialog

U-CAM: Visual Explanation using Uncertainty based Class Activation Maps

no code implementations ICCV 2019 Badri N. Patro, Mayank Lunayach, Shivansh Patel, Vinay P. Namboodiri

These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions.

Probabilistic Deep Learning Question Answering +1

Curriculum based Dropout Discriminator for Domain Adaptation

1 code implementation24 Jul 2019 Vinod Kumar Kurmi, Vipul Bajaj, Venkatesh K Subramanian, Vinay P. Namboodiri

However, here we suggest that rather than using a point estimate, it would be useful if a distribution based discriminator could be used to bridge this gap.

Domain Adaptation

Attending to Discriminative Certainty for Domain Adaptation

1 code implementation CVPR 2019 Vinod Kumar Kurmi, Shanu Kumar, Vinay P. Namboodiri

In this paper, we aim to solve for unsupervised domain adaptation of classifiers where we have access to label information for the source domain while these are not available for a target domain.

Unsupervised Domain Adaptation

InfoRL: Interpretable Reinforcement Learning using Information Maximization

no code implementations24 May 2019 Aadil Hayat, Utsav Singh, Vinay P. Namboodiri

Recent advances in reinforcement learning have proved that given an environment we can learn to perform a task in that environment if we have access to some form of a reward function (dense, sparse or derived from IRL).

reinforcement-learning

Play and Prune: Adaptive Filter Pruning for Deep Model Compression

1 code implementation11 May 2019 Pravendra Singh, Vinay Kumar Verma, Piyush Rai, Vinay P. Namboodiri

Our framework, called Play and Prune (PP), jointly prunes and fine-tunes CNN model parameters, with an adaptive pruning rate, while maintaining the model's predictive performance.

Model Compression

Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal

no code implementations14 Apr 2019 Abhishek Joshi, Vinay P. Namboodiri

Finally through this synthesis approach we obtain a comparable set of abnormal samples that can be used for training the CNN for the classification of normal vs abnormal samples.

Activity Recognition Data Augmentation

Looking back at Labels: A Class based Domain Adaptation Technique

1 code implementation2 Apr 2019 Vinod Kumar Kurmi, Vinay P. Namboodiri

Our observation relies on the analysis that shows that if the discriminator has access to all the information available including the class structure present in the source dataset, then it can guide the transformation of features of the target set of classes to a more structure adapted space.

Domain Adaptation Image Classification +1

CVIT-MT Systems for WAT-2018

no code implementations PACLIC 2018 Jerin Philip, Vinay P. Namboodiri, C. V. Jawahar

This document describes the machine translation system used in the submissions of IIIT-Hyderabad CVIT-MT for the WAT-2018 English-Hindi translation task.

Machine Translation Translation

HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs

1 code implementation CVPR 2019 Pravendra Singh, Vinay Kumar Verma, Piyush Rai, Vinay P. Namboodiri

We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels.

Accuracy Booster: Performance Boosting using Feature Map Re-calibration

no code implementations11 Mar 2019 Pravendra Singh, Pratik Mazumder, Vinay P. Namboodiri

Recently researchers have tried to boost the performance of CNNs by re-calibrating the feature maps produced by these filters, e. g., Squeeze-and-Excitation Networks (SENets).

General Classification Object Detection

PUTWorkbench: Analysing Privacy in AI-intensive Systems

no code implementations5 Feb 2019 Saurabh Srivastava, Vinay P. Namboodiri, T. V. Prabhakar

AI intensive systems that operate upon user data face the challenge of balancing data utility with privacy concerns.

Leveraging Filter Correlations for Deep Model Compression

no code implementations26 Nov 2018 Pravendra Singh, Vinay Kumar Verma, Piyush Rai, Vinay P. Namboodiri

We present a filter correlation based model compression approach for deep convolutional neural networks.

Model Compression Object Detection

Stability Based Filter Pruning for Accelerating Deep CNNs

no code implementations20 Nov 2018 Pravendra Singh, Vinay Sameer Raja Kadi, Nikhil Verma, Vinay P. Namboodiri

Convolutional neural networks (CNN) have achieved impressive performance on the wide variety of tasks (classification, detection, etc.)

Model Compression

Multi-layer Pruning Framework for Compressing Single Shot MultiBox Detector

no code implementations20 Nov 2018 Pravendra Singh, Manikandan. R, Neeraj Matiyali, Vinay P. Namboodiri

Additionally, we also empirically show our method's adaptability for classification based architecture VGG16 on datasets CIFAR and German Traffic Sign Recognition Benchmark (GTSRB) achieving a compression rate of 125X and 200X with the reduction in flops by 90. 50% and 96. 6% respectively with no loss of accuracy.

Traffic Sign Detection Traffic Sign Recognition

Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator

2 code implementations COLING 2018 Badri N. Patro, Vinod K. Kurmi, Sandeep Kumar, Vinay P. Namboodiri

One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.

Paraphrase Generation Sentence Embedding +2

No Modes left behind: Capturing the data distribution effectively using GANs

1 code implementation2 Feb 2018 Shashank Sharma, Vinay P. Namboodiri

Given a set of data that has an imbalance in the distribution, the networks are susceptible to missing modes and not capturing the data distribution.

Image Generation

Compact Environment-Invariant Codes for Robust Visual Place Recognition

no code implementations23 Sep 2017 Unnat Jain, Vinay P. Namboodiri, Gaurav Pandey

The modified system learns (in a supervised setting) compact binary codes from image feature descriptors.

Visual Place Recognition

Learning to Estimate Pose by Watching Videos

1 code implementation13 Apr 2017 Prabuddha Chakraborty, Vinay P. Namboodiri

In this paper we propose a technique for obtaining coarse pose estimation of humans in an image that does not require any manual supervision.

Action Recognition Pose Estimation

Active learning with version spaces for object detection

no code implementations22 Nov 2016 Soumya Roy, Vinay P. Namboodiri, Arijit Biswas

Previous works on object detection model the problem as a structured regression problem which ranks the correct bounding boxes more than the background ones.

Active Learning Object Detection +1

Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets

no code implementations26 Mar 2016 Ayush Mittal, Anant Raj, Vinay P. Namboodiri, Tinne Tuytelaars

Most methods for unsupervised domain adaptation proposed in the literature to date, assume that the set of classes present in the target domain is identical to the set of classes present in the source domain.

General Classification Unsupervised Domain Adaptation

Subspace Alignment Based Domain Adaptation for RCNN Detector

no code implementations20 Jul 2015 Anant Raj, Vinay P. Namboodiri, Tinne Tuytelaars

In this paper, we propose subspace alignment based domain adaptation of the state of the art RCNN based object detector.

Object Detection Unsupervised Domain Adaptation

Mind the Gap: Subspace based Hierarchical Domain Adaptation

no code implementations16 Jan 2015 Anant Raj, Vinay P. Namboodiri, Tinne Tuytelaars

Domain adaptation techniques aim at adapting a classifier learnt on a source domain to work on the target domain.

Domain Adaptation

Object Classification with Adaptable Regions

no code implementations CVPR 2014 Hakan Bilen, Marco Pedersoli, Vinay P. Namboodiri, Tinne Tuytelaars, Luc van Gool

In classification of objects substantial work has gone into improving the low level representation of an image by considering various aspects such as different features, a number of feature pooling and coding techniques and considering different kernels.

Classification General Classification

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