Search Results for author: Piyush Rai

Found 60 papers, 15 papers with code

Novel Class Discovery without Forgetting

no code implementations21 Jul 2022 K J Joseph, Sujoy Paul, Gaurav Aggarwal, Soma Biswas, Piyush Rai, Kai Han, Vineeth N Balasubramanian

Inspired by this, we identify and formulate a new, pragmatic problem setting of NCDwF: Novel Class Discovery without Forgetting, which tasks a machine learning model to incrementally discover novel categories of instances from unlabeled data, while maintaining its performance on the previously seen categories.

Novel Class Discovery

Bayesian Federated Learning via Predictive Distribution Distillation

no code implementations15 Jun 2022 Shrey Bhatt, Aishwarya Gupta, Piyush Rai

Point estimation of the model parameters at the clients does not take into account the uncertainty in the models estimated at each client.

Active Learning Federated Learning +1

Spacing Loss for Discovering Novel Categories

1 code implementation22 Apr 2022 K J Joseph, Sujoy Paul, Gaurav Aggarwal, Soma Biswas, Piyush Rai, Kai Han, Vineeth N Balasubramanian

Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes.

Novel Class Discovery

Semi-Supervised Super-Resolution

no code implementations18 Apr 2022 Ankur Singh, Piyush Rai

The proposed semi-supervised technique can be used as a plug-and-play module with any supervised GAN-based Super-Resolution method to enhance its performance.


DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents

1 code implementation2 Jan 2022 Kushagra Pandey, Avideep Mukherjee, Piyush Rai, Abhishek Kumar

Furthermore, we show that the proposed model can generate high-resolution samples and exhibits synthesis quality comparable to state-of-the-art models on standard benchmarks.

Image Generation

SITA: Single Image Test-time Adaptation

no code implementations4 Dec 2021 Ansh Khurana, Sujoy Paul, Piyush Rai, Soma Biswas, Gaurav Aggarwal

In Test-time Adaptation (TTA), given a model trained on some source data, the goal is to adapt it to make better predictions for test instances from a different distribution.

NeurInt : Learning to Interpolate through Neural ODEs

no code implementations7 Nov 2021 Avinandan Bose, Aniket Das, Yatin Dandi, Piyush Rai

In this work, we propose a novel generative model that learns a flexible non-parametric prior over interpolation trajectories, conditioned on a pair of source and target images.

Image Generation

Hypernetworks for Continual Semi-Supervised Learning

no code implementations5 Oct 2021 Dhanajit Brahma, Vinay Kumar Verma, Piyush Rai

Further, we present $\textit{Semi-Split CIFAR-10}$, a new benchmark for continual semi-supervised learning, obtained by modifying the $\textit{Split CIFAR-10}$ dataset, in which the tasks with labelled and unlabelled data arrive sequentially.

Continual Learning Split-CIFAR-10

NeurInt-Learning Interpolation by Neural ODEs

no code implementations NeurIPS Workshop DLDE 2021 Avinandan Bose, Aniket Das, Yatin Dandi, Piyush Rai

A range of applications require learning image generation models whose latent space effectively captures the high-level factors of variation in the data distribution, which can be judged by its ability to interpolate between images smoothly.

Image Generation

Fine-Grained Emotion Prediction by Modeling Emotion Definitions

1 code implementation26 Jul 2021 Gargi Singh, Dhanajit Brahma, Piyush Rai, Ashutosh Modi

In this paper, we propose a new framework for fine-grained emotion prediction in the text through emotion definition modeling.

Language Modelling Masked Language Modeling +1

Knowledge Consolidation based Class Incremental Online Learning with Limited Data

no code implementations12 Jun 2021 Mohammed Asad Karim, Vinay Kumar Verma, Pravendra Singh, Vinay Namboodiri, Piyush Rai

In our approach, we learn robust representations that are generalizable across tasks without suffering from the problems of catastrophic forgetting and overfitting to accommodate future classes with limited samples.

class-incremental learning Incremental Learning +2

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

Variational Rejection Particle Filtering

no code implementations29 Mar 2021 Rahul Sharma, Soumya Banerjee, Dootika Vats, Piyush Rai

We present a variational inference (VI) framework that unifies and leverages sequential Monte-Carlo (particle filtering) with \emph{approximate} rejection sampling to construct a flexible family of variational distributions.

Variational Inference

Efficient Feature Transformations for Discriminative and Generative Continual Learning

1 code implementation CVPR 2021 Vinay Kumar Verma, Kevin J Liang, Nikhil Mehta, Piyush Rai, Lawrence Carin

However, the growth in the number of additional parameters of many of these types of methods can be computationally expensive at larger scales, at times prohibitively so.

Continual Learning

Few-Shot Lifelong Learning

no code implementations1 Mar 2021 Pratik Mazumder, Pravendra Singh, Piyush Rai

Our method selects very few parameters from the model for training every new set of classes instead of training the full model.

Continual Learning

A Unified Bayesian Framework for Discriminative and Generative Continual Learning

no code implementations1 Jan 2021 Abhishek Kumar, Sunabha Chatterjee, Piyush Rai

Two notable directions among the recent advances in continual learning with neural networks are (1) variational Bayes based regularization by learning priors from previous tasks, and, (2) learning the structure of deep networks to adapt to new tasks.

Continual Learning

Quantile Regularization : Towards Implicit Calibration of Regression Models

no code implementations1 Jan 2021 Saiteja Utpala, Piyush Rai

We provide a detailed formal analysis of the \emph{side-effects} of Isotonic Regression when used for regression calibration.

Calibrating CNNs for Lifelong Learning

no code implementations NeurIPS 2020 Pravendra Singh, Vinay Kumar Verma, Pratik Mazumder, Lawrence Carin, Piyush Rai

Further, our approach does not require storing data samples from the old tasks, which is done by many replay based methods.

Continual Learning

Towards Zero-Shot Learning with Fewer Seen Class Examples

no code implementations14 Nov 2020 Vinay Kumar Verma, Ashish Mishra, Anubha Pandey, Hema A. Murthy, Piyush Rai

We present a meta-learning based generative model for zero-shot learning (ZSL) towards a challenging setting when the number of training examples from each \emph{seen} class is very few.

Meta-Learning Zero-Shot Learning

Temperature Scaling for Quantile Calibration

no code implementations NeurIPS Workshop ICBINB 2020 Saiteja Utpala, Piyush Rai

Deep learning models are often poorly calibrated, i. e., they may produce overconfident predictions that are wrong, implying that their uncertainty estimates are unreliable.


Generalized Adversarially Learned Inference

no code implementations15 Jun 2020 Yatin Dandi, Homanga Bharadhwaj, Abhishek Kumar, Piyush Rai

Recent approaches, such as ALI and BiGAN frameworks, develop methods of inference of latent variables in GANs by adversarially training an image generator along with an encoder to match two joint distributions of image and latent vector pairs.

P-SIF: Document Embeddings Using Partition Averaging

1 code implementation18 May 2020 Vivek Gupta, Ankit Saw, Pegah Nokhiz, Praneeth Netrapalli, Piyush Rai, Partha Talukdar

One of the key reasons is that a longer document is likely to contain words from many different topics; hence, creating a single vector while ignoring all the topical structure is unlikely to yield an effective document representation.

Graph Representation Learning via Ladder Gamma Variational Autoencoders

1 code implementation3 Apr 2020 Arindam Sarkar, Nikhil Mehta, Piyush Rai

In addition to leveraging the representational power of multiple layers of stochastic variables via the ladder VAE architecture, our framework offers the following benefits: (1) Unlike existing ladder VAE architectures based on real-valued latent variables, the gamma-distributed latent variables naturally result in non-negativity and sparsity of the learned embeddings, and facilitate their direct interpretation as membership of nodes into (possibly multiple) communities/topics; (2) A novel recognition model for our gamma ladder VAE architecture allows fast inference of node embeddings; and (3) The framework also extends naturally to incorporate node side information (features and/or labels).

Graph Representation Learning Link Prediction

Quantile Regularization: Towards Implicit Calibration of Regression Models

no code implementations28 Feb 2020 Saiteja Utpala, Piyush Rai

It is therefore desirable to have models that produce predictive uncertainty estimates that are reliable.

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 +4

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

On the relationship between multitask neural networks and multitask Gaussian Processes

no code implementations12 Dec 2019 Karthikeyan K, Shubham Kumar Bharti, Piyush Rai

Despite the effectiveness of multitask deep neural network (MTDNN), there is a limited theoretical understanding on how the information is shared across different tasks in MTDNN.

Bayesian Inference Gaussian Processes

Bayesian Structure Adaptation for Continual Learning

1 code implementation8 Dec 2019 Abhishek Kumar, Sunabha Chatterjee, Piyush Rai

Two notable directions among the recent advances in continual learning with neural networks are ($i$) variational Bayes based regularization by learning priors from previous tasks, and, ($ii$) learning the structure of deep networks to adapt to new tasks.

Continual Learning

Learning to Recommend from Sparse Data via Generative User Feedback

no code implementations ICLR 2020 Wenlin Wang, Hongteng Xu, Ruiyi Zhang, Wenqi Wang, Piyush Rai, Lawrence Carin

To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback.

Collaborative Filtering Recommendation Systems

Refined $α$-Divergence Variational Inference via Rejection Sampling

no code implementations17 Sep 2019 Rahul Sharma, Abhishek Kumar, Piyush Rai

Our inference method is based on a crucial observation that $D_\infty(p||q)$ equals $\log M(\theta)$ where $M(\theta)$ is the optimal value of the RS constant for a given proposal $q_\theta(x)$.

Variational Inference

A Meta-Learning Framework for Generalized Zero-Shot Learning

1 code implementation10 Sep 2019 Vinay Kumar Verma, Dhanajit Brahma, Piyush Rai

Our proposed model yields significant improvements on standard ZSL as well as more challenging GZSL setting.

Generalized Zero-Shot Learning Meta-Learning

Stochastic Blockmodels meet Graph Neural Networks

no code implementations Proceedings of the 36th International Conference on Machine Learning 2019 Nikhil Mehta, Lawrence Carin, Piyush Rai

Although we develop this framework for a particular type of SBM, namely the \emph{overlapping} stochastic blockmodel, the proposed framework can be adapted readily for other types of SBMs.

Link Prediction

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

Variational Autoencoders for Sparse and Overdispersed Discrete Data

1 code implementation2 May 2019 He Zhao, Piyush Rai, Lan Du, Wray Buntine, Mingyuan Zhou

Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data.

Collaborative Filtering Multi-Label Learning +1

Generative Model for Zero-Shot Sketch-Based Image Retrieval

no code implementations18 Apr 2019 Vinay Kumar Verma, Aakansha Mishra, Ashish Mishra, Piyush Rai

We present a probabilistic model for Sketch-Based Image Retrieval (SBIR) where, at retrieval time, we are given sketches from novel classes, that were not present at training time.

Image Generation Sketch-Based Image Retrieval

Deep Topic Models for Multi-label Learning

no code implementations13 Apr 2019 Rajat Panda, Ankit Pensia, Nikhil Mehta, Mingyuan Zhou, Piyush Rai

We present a probabilistic framework for multi-label learning based on a deep generative model for the binary label vector associated with each observation.

Multi-Label Learning Topic Models

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.

Small-Variance Asymptotics for Nonparametric Bayesian Overlapping Stochastic Blockmodels

no code implementations10 Jul 2018 Gundeep Arora, Anupreet Porwal, Kanupriya Agarwal, Avani Samdariya, Piyush Rai

The latent feature relational model (LFRM) is a generative model for graph-structured data to learn a binary vector representation for each node in the graph.

A Generative Approach to Zero-Shot and Few-Shot Action Recognition

no code implementations27 Jan 2018 Ashish Mishra, Vinay Kumar Verma, M Shiva Krishna Reddy, Arulkumar S, Piyush Rai, Anurag Mittal

In particular, we assume that the distribution parameters for any action class in the visual space can be expressed as a linear combination of a set of basis vectors where the combination weights are given by the attributes of the action class.

Few Shot Action Recognition Generalized Zero-Shot Learning +1

Generalized Zero-Shot Learning via Synthesized Examples

no code implementations CVPR 2018 Vinay Kumar Verma, Gundeep Arora, Ashish Mishra, Piyush Rai

Our model's ability to generate and leverage examples from unseen classes to train the classification model naturally helps to mitigate the bias towards predicting seen classes in generalized zero-shot learning settings.

General Classification Generalized Zero-Shot Learning

Leveraging Distributional Semantics for Multi-Label Learning

no code implementations18 Sep 2017 Rahul Wadbude, Vivek Gupta, Piyush Rai, Nagarajan Natarajan, Harish Karnick, Prateek Jain

Our approach is novel in that it highlights interesting connections between label embedding methods used for multi-label learning and paragraph/document embedding methods commonly used for learning representations of text data.

Document Embedding Multi-Label Learning +2

A Simple Exponential Family Framework for Zero-Shot Learning

2 code implementations25 Jul 2017 Vinay Kumar Verma, Piyush Rai

We model each class-conditional distribution as an exponential family distribution and the parameters of the distribution of each seen/unseen class are defined as functions of the respective observed class attributes.

Few-Shot Learning Zero-Shot Learning

Earliness-Aware Deep Convolutional Networks for Early Time Series Classification

no code implementations14 Nov 2016 Wenlin Wang, Changyou Chen, Wenqi Wang, Piyush Rai, Lawrence Carin

Unlike most existing methods for early classification of time series data, that are designed to solve this problem under the assumption of the availability of a good set of pre-defined (often hand-crafted) features, our framework can jointly perform feature learning (by learning a deep hierarchy of \emph{shapelets} capturing the salient characteristics in each time series), along with a dynamic truncation model to help our deep feature learning architecture focus on the early parts of each time series.

Classification General Classification +1

Scalable Bayesian Non-Negative Tensor Factorization for Massive Count Data

no code implementations18 Aug 2015 Changwei Hu, Piyush Rai, Changyou Chen, Matthew Harding, Lawrence Carin

We present a Bayesian non-negative tensor factorization model for count-valued tensor data, and develop scalable inference algorithms (both batch and online) for dealing with massive tensors.

Zero-Truncated Poisson Tensor Factorization for Massive Binary Tensors

no code implementations18 Aug 2015 Changwei Hu, Piyush Rai, Lawrence Carin

We present a scalable Bayesian model for low-rank factorization of massive tensors with binary observations.

Bayesian Inference

Simultaneously Leveraging Output and Task Structures for Multiple-Output Regression

no code implementations NeurIPS 2012 Piyush Rai, Abhishek Kumar, Hal Daume

In this paper, we present a multiple-output regression model that leverages the covariance structure of the functions (i. e., how the multiple functions are related with each other) as well as the conditional covariance structure of the outputs.

Message-Passing for Approximate MAP Inference with Latent Variables

no code implementations NeurIPS 2011 Jiarong Jiang, Piyush Rai, Hal Daume

We consider a general inference setting for discrete probabilistic graphical models where we seek maximum a posteriori (MAP) estimates for a subset of the random variables (max nodes), marginalizing over the rest (sum nodes).

Co-regularized Multi-view Spectral Clustering

no code implementations NeurIPS 2011 Abhishek Kumar, Piyush Rai, Hal Daume

In many clustering problems, we have access to multiple views of the data each of which could be individually used for clustering.

Multi-Label Prediction via Sparse Infinite CCA

no code implementations NeurIPS 2009 Piyush Rai, Hal Daume

Canonical Correlation Analysis (CCA) is a useful technique for modeling dependencies between two (or more) sets of variables.

Supervised dimensionality reduction

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