Search Results for author:
Found 65 papers, 16 papers with code
VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
Most of the existing methods primarily focus on lifelong learning within a static environment and lack the ability to mitigate forgetting in a quickly-changing dynamic environment.
SpectFormer: Frequency and Attention is what you need in a Vision Transformer
Vision transformers have been applied successfully for image recognition tasks.
Streaming LifeLong Learning With Any-Time Inference
Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups.
Compressing Video Calls using Synthetic Talking Heads
We use a state-of-the-art face reenactment network to detect key points in the non-pivot frames and transmit them to the receiver.
Learning Speaker-specific Lip-to-Speech Generation
This work aims to understand the correlation/mapping between speech and the sequence of lip movement of individual speakers in an unconstrained and large vocabulary.
Gradient Based Activations for Accurate Bias-Free Learning
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
We propose a novel approach (CIOSL) for the class-incremental learning in an \emph{online streaming setting} to address these challenges.
Intelligent Video Editing: Incorporating Modern Talking Face Generation Algorithms in a Video Editor
Our evaluations show a clear improvement in the efficiency of using human editors and an improved video generation quality.
Attentive Contractive Flow with Lipschitz-constrained Self-Attention
Normalizing flows provide an elegant method for obtaining tractable density estimates from distributions by using invertible transformations.
More Parameters? No Thanks!
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.
Prb-GAN: A Probabilistic Framework for GAN Modelling
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.
Exploring Dropout Discriminator for Domain Adaptation
Among the methodologies used, that of adversarial learning is widely applied to solve many deep learning problems along with domain adaptation.
Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation
Our approach significantly improves their performance and further reduces the model biases in the limited data regime.
Rectification-based Knowledge Retention for Continual Learning
Our proposed method uses weight rectifications and affine transformations in order to adapt the model to different tasks that arrive sequentially.
Do Not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting
We define distillation losses in terms of aleatoric uncertainty and self-attention.
Exploring Pair-Wise NMT for Indian Languages
In this paper, we address the task of improving pair-wise machine translation for specific low resource Indian languages.
RNNP: A Robust Few-Shot Learning Approach
Our method relies on generating robust prototypes from a set of few examples.
SHAD3S: A model to Sketch, Shade and Shadow
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
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.
Revisiting Low Resource Status of Indian Languages in Machine Translation
Through this paper, we provide and analyse an automated framework to obtain such a corpus for Indian language neural machine translation (NMT) systems.
A Multilingual Parallel Corpora Collection Effort for Indian Languages
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.
Learning to Switch CNNs with Model Agnostic Meta Learning for Fine Precision Visual Servoing
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.
Improving Few-Shot Learning using Composite Rotation based Auxiliary Task
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.
Passive Batch Injection Training Technique: Boosting Network Performance by Injecting Mini-Batches from a different Data Distribution
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.
AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings
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.
Deep Bayesian Network for Visual Question Generation
This is a Bayesian framework and the results show a remarkable similarity to natural questions as validated by a human study.
Uncertainty based Class Activation Maps for Visual Question Answering
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.
Robust Explanations for Visual Question Answering
Our model explains the answers obtained through a VQA model by providing visual and textual explanations.
A "Network Pruning Network" Approach to Deep Model Compression
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.
Cooperative Initialization based Deep Neural Network Training
In this paper, we have proposed a cooperative initialization for training the deep network using ReLU activation function to improve the network performance.
Revisiting Paraphrase Question Generator using Pairwise Discriminator
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.
Deep Exemplar Networks for VQA and VQG
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.
Jointly Trained Image and Video Generation using Residual Vectors
The proposed model allows minor variations in content across frames while maintaining the temporal dependence through latent vectors encoding the pose or motion features.
Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA
It also results in a good improvement in rank correlation metric on the VQA task.
Can I teach a robot to replicate a line art
Line art is arguably one of the fundamental and versatile modes of expression.
Dynamic Attention Networks for Task Oriented Grounding
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
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.
Probabilistic framework for solving Visual Dialog
In this paper, we propose a probabilistic framework for solving the task of `Visual Dialog'.
Ranked #1 on
Common Sense Reasoning
on Visual Dialog v0.9
U-CAM: Visual Explanation using Uncertainty based Class Activation Maps
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.
A Baseline Neural Machine Translation System for Indian Languages
We present a simple, yet effective, Neural Machine Translation system for Indian languages.
Curriculum based Dropout Discriminator for Domain Adaptation
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.
Ranked #29 on
Domain Adaptation
on Office-31
Attending to Discriminative Certainty for Domain Adaptation
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.
Ranked #10 on
Domain Adaptation
on ImageCLEF-DA
InfoRL: Interpretable Reinforcement Learning using Information Maximization
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).
Play and Prune: Adaptive Filter Pruning for Deep Model Compression
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.
Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal
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.
Looking back at Labels: A Class based Domain Adaptation Technique
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.
Ranked #13 on
Domain Adaptation
on ImageCLEF-DA
CVIT-MT Systems for WAT-2018
This document describes the machine translation system used in the submissions of IIIT-Hyderabad CVIT-MT for the WAT-2018 English-Hindi translation task.
Accuracy Booster: Performance Boosting using Feature Map Re-calibration
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).
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels.
PUTWorkbench: Analysing Privacy in AI-intensive Systems
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
We present a filter correlation based model compression approach for deep convolutional neural networks.
Stability Based Filter Pruning for Accelerating Deep CNNs
Convolutional neural networks (CNN) have achieved impressive performance on the wide variety of tasks (classification, detection, etc.)
Multi-layer Pruning Framework for Compressing Single Shot MultiBox Detector
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.
Multimodal Differential Network for Visual Question Generation
Generating natural questions from an image is a semantic task that requires using visual and language modality to learn multimodal representations.
Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
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.
Differential Attention for Visual Question Answering
A number of methods have focused on solving this problem by using image based attention.
No Modes left behind: Capturing the data distribution effectively using GANs
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.
POLICY DRIVEN GENERATIVE ADVERSARIAL NETWORKS FOR ACCENTED SPEECH GENERATION
In this paper, we propose the generation of accented speech using generative adversarial networks.
Compact Environment-Invariant Codes for Robust Visual Place Recognition
The modified system learns (in a supervised setting) compact binary codes from image feature descriptors.
Learning to Estimate Pose by Watching Videos
In this paper we propose a technique for obtaining coarse pose estimation of humans in an image that does not require any manual supervision.
Active learning with version spaces for object detection
Previous works on object detection model the problem as a structured regression problem which ranks the correct bounding boxes more than the background ones.
Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets
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.
Subspace Alignment Based Domain Adaptation for RCNN Detector
In this paper, we propose subspace alignment based domain adaptation of the state of the art RCNN based object detector.
Mind the Gap: Subspace based Hierarchical Domain Adaptation
Domain adaptation techniques aim at adapting a classifier learnt on a source domain to work on the target domain.
Object Classification with Adaptable Regions
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.
