Search Results - "Namboodiri, Vinay P."

Attending to Discriminative Certainty for Domain Adaptation by Kurmi, Vinod Kumar, Kumar, Shanu, Namboodiri, Vinay P.

“…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…”
Get full text

Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis by Prajwal, K R, Mukhopadhyay, Rudrabha, Namboodiri, Vinay P., Jawahar, C.V.

“…Humans involuntarily tend to infer parts of the conversation from lip movements when the speech is absent or corrupted by external noise. In this work, we…”
Get full text

AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings by Mazumder, Pratik, Sing, Pravendra, Kumar Parida, Kranti, Namboodiri, Vinay P.

“…In this paper, we propose a novel approach for generalized zero-shot learning in a multi-modal setting, where we have novel classes ofaudio/video during…”
Get full text

Rectification-Based Knowledge Retention for Task Incremental Learning by Mazumder, Pratik, Singh, Pravendra, Rai, Piyush, Namboodiri, Vinay P.

“…In the task incremental learning problem, deep learning models suffer from catastrophic forgetting of previously seen classes/tasks as they are trained on new…”
Get full text

Differential Attention for Visual Question Answering by Patro, Badri, Namboodiri, Vinay P.

“…In this paper we aim to answer questions based on images when provided with a dataset of question-answer pairs for a number of images during training. A number…”
Get full text

Domain Impression: A Source Data Free Domain Adaptation Method by Kurmi, Vinod K, Subramanian, Venkatesh K, Namboodiri, Vinay P

“…Unsupervised Domain adaptation methods solve the adaptation problem for an unlabeled target set, assuming that the source dataset is available with all labels…”
Get full text

Uncertainty Class Activation Map (U-CAM) Using Gradient Certainty Method by Patro, Badri Narayana, Lunayach, Mayank, Namboodiri, Vinay P.

“…Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that…”
Get full text

HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs by Singh, Pravendra, Verma, Vinay Kumar, Rai, Piyush, Namboodiri, Vinay P.

“…We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous…”
Get full text

Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning by Singh, Pravendra, Verma, Vinay Kumar, Rai, Piyush, Namboodiri, Vinay P.

“…While convolutional neural networks (CNNs) have achieved remarkable performance on various supervised and unsupervised learning tasks, they typically consist…”
Get full text

Leveraging Filter Correlations for Deep Model Compression by Singh, Pravendra, Verma, Vinay Kumar, Rai, Piyush, Namboodiri, Vinay P.

“…We present a filter correlation based model compression approach for deep convolutional neural networks. Our approach iteratively identifies pairs of filters…”
Get full text

HetConv: Beyond Homogeneous Convolution Kernels for Deep CNNs by Singh, Pravendra, Verma, Vinay Kumar, Rai, Piyush, Namboodiri, Vinay P.

“…While usage of convolutional neural networks (CNN) is widely prevalent, methods proposed so far always have considered homogeneous kernels for this task. In…”
Get full text

RNNP: A Robust Few-Shot Learning Approach by Mazumder, Pratik, Singh, Pravendra, Namboodiri, Vinay P.

“…Learning from a few examples is an important practical aspect of training classifiers. Various works have examined this aspect quite well. However, all…”
Get full text

Rectification-based Knowledge Retention for Continual Learning by Singh, Pravendra, Mazumder, Pratik, Rai, Piyush, Namboodiri, Vinay P.

“…Deep learning models suffer from catastrophic forgetting when trained in an incremental learning setting. In this work, we propose a novel approach to address…”
Get full text

Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation by Mazumder, Pratik, Singh, Pravendra, Namboodiri, Vinay P.

“…Deep learning models generally learn the biases present in the training data. Researchers have proposed several approaches to mitigate such biases and make the…”
Get full text

Improving Few-Shot Learning using Composite Rotation based Auxiliary Task by Mazumder, Pratik, Singh, Pravendra, Namboodiri, Vinay P.

“…In this paper, we propose an approach to improve few-shot classification performance using a composite rotation based auxiliary task. Few-shot classification…”
Get full text

Robust Explanations for Visual Question Answering by Patro, Badri N., Patel, Shivansh, Namboodiri, Vinay P.

“…In this paper, we propose a method to obtain robust explanations for visual question answering(VQA) that correlate well with the answers. Our model explains…”
Get full text

Speech Prediction in Silent Videos Using Variational Autoencoders by Yadav, Ravindra, Sardana, Ashish, Namboodiri, Vinay P, Hegde, Rajesh M

“…Understanding the relationship between the auditory and visual signals is crucial for many different applications ranging from computer-generated imagery (CGI)…”
Get full text

Accuracy Booster: Performance Boosting using Feature Map Re-calibration by Singh, Pravendra, Mazumder, Pratik, Namboodiri, Vinay P.

“…Convolution Neural Networks (CNN) have been extremely successful in solving intensive computer vision tasks. The convolutional filters used in CNNs have played…”
Get full text

Cooperative Initialization based Deep Neural Network Training by Singh, Pravendra, Varshney, Munender, Namboodiri, Vinay P.

“…Researchers have proposed various activation functions. These activation functions help the deep network to learn non-linear behavior with a significant effect…”
Get full text

Learning Speaker-specific Lip-to-Speech Generation by Varshney, Munender, Yadav, Ravindra, Namboodiri, Vinay P., Hegde, Rajesh M

“…Understanding the lip movement and inferring the speech from it is notoriously difficult for the common person. The task of accurate lip-reading gets help from…”
Get full text