134 citations · 459 across the 38 of their papers we have counts for
53 papers
Shortcut Invariance: Targeted Jacobian Regularization in Disentangled Latent Space
Shivam Pal, Sakshi Varshney, Piyush Rai
Deep neural networks are prone to learning shortcuts, spurious correlations present in the training data that undermine out-of-distribution (OOD) generalization. Most prior work mi…
NOVO: Unlearning-Compliant Vision Transformers
Soumya Roy, Soumya Banerjee, Vinay Verma +3
Machine unlearning (MUL) refers to the problem of making a pre-trained model selectively forget some training instances or class(es) while retaining performance on the remaining da…
Spatio-Temporal Forecasting of PM2.5 via Spatial-Diffusion guided Encoder-Decoder Architecture
Malay Pandey, Vaishali Jain, Nimit Godhani +2
In many problem settings that require spatio-temporal forecasting, the values in the time-series not only exhibit spatio-temporal correlations but are also influenced by spatial di…
Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization
Shivam Pal, Aishwarya Gupta, Saqib Sarwar +1
Federated Learning (FL) has emerged as a promising method to collaboratively learn from decentralized and heterogeneous data available at different clients without the requirement…
Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage
Aishwarya Gupta, Indranil Saha, Piyush Rai
Rigorous testing of machine learning models is necessary for trustworthy deployments. We present a novel black-box approach for generating test-suites for robust testing of deep ne…
VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
Soumya Banerjee, Vinay K. Verma, Avideep Mukherjee +3
Lifelong learning or continual learning is the problem of training an AI agent continuously while also preventing it from forgetting its previously acquired knowledge. Streaming li…
A Probabilistic Framework for Lifelong Test-Time Adaptation
Dhanajit Brahma, Piyush Rai
Test-time adaptation (TTA) is the problem of updating a pre-trained source model at inference time given test input(s) from a different target domain. Most existing TTA approaches…
Novel Class Discovery without Forgetting
K J Joseph, Sujoy Paul, Gaurav Aggarwal +4
Humans possess an innate ability to identify and differentiate instances that they are not familiar with, by leveraging and adapting the knowledge that they have acquired so far. I…
Federated Learning with Uncertainty via Distilled Predictive Distributions
Shrey Bhatt, Aishwarya Gupta, Piyush Rai
Most existing federated learning methods are unable to estimate model/predictive uncertainty since the client models are trained using the standard loss function minimization appro…
Spacing Loss for Discovering Novel Categories
K J Joseph, Sujoy Paul, Gaurav Aggarwal +4
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 fro…
Semi-Supervised Super-Resolution
Ankur Singh, Piyush Rai
Super-Resolution is the technique to improve the quality of a low-resolution photo by boosting its plausible resolution. The computer vision community has extensively explored the…
DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents
Kushagra Pandey, Avideep Mukherjee, Piyush Rai +1
Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable late…
SITA: Single Image Test-time Adaptation
Ansh Khurana, Sujoy Paul, Piyush Rai +2
In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source. Crucially,…
Hypernetworks for Continual Semi-Supervised Learning
Dhanajit Brahma, Vinay Kumar Verma, Piyush Rai
Learning from data sequentially arriving, possibly in a non i.i.d. way, with changing task distribution over time is called continual learning. Much of the work thus far in continu…
Fine-Grained Emotion Prediction by Modeling Emotion Definitions
Gargi Singh, Dhanajit Brahma, Piyush Rai +1
In this paper, we propose a new framework for fine-grained emotion prediction in the text through emotion definition modeling. Our approach involves a multi-task learning framework…
Knowledge Consolidation based Class Incremental Online Learning with Limited Data
Mohammed Asad Karim, Vinay Kumar Verma, Pravendra Singh +2
We propose a novel approach for class incremental online learning in a limited data setting. This problem setting is challenging because of the following constraints: (1) Classes a…
Rectification-based Knowledge Retention for Continual Learning
Pravendra Singh, Pratik Mazumder, Piyush Rai +1
Deep learning models suffer from catastrophic forgetting when trained in an incremental learning setting. In this work, we propose a novel approach to address the task incremental…
Variational Rejection Particle Filtering
Rahul Sharma, Soumya Banerjee, Dootika Vats +1
We present a variational inference (VI) framework that unifies and leverages sequential Monte-Carlo (particle filtering) with \emph{approximate} rejection sampling to construct a f…
Efficient Feature Transformations for Discriminative and Generative Continual Learning
Vinay Kumar Verma, Kevin J Liang, Nikhil Mehta +2
As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critica…
CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
Sakshi Varshney, Vinay Kumar Verma, Srijith P K +2
We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is ba…
Few-Shot Lifelong Learning
Pratik Mazumder, Pravendra Singh, Piyush Rai
Many real-world classification problems often have classes with very few labeled training samples. Moreover, all possible classes may not be initially available for training, and m…
Towards Zero-Shot Learning with Fewer Seen Class Examples
Vinay Kumar Verma, Ashish Mishra, Anubha Pandey +2
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 ver…
Generalized Adversarially Learned Inference
Yatin Dandi, Homanga Bharadhwaj, Abhishek Kumar +1
Allowing effective inference of latent vectors while training GANs can greatly increase their applicability in various downstream tasks. Recent approaches, such as ALI and BiGAN fr…
P-SIF: Document Embeddings Using Partition Averaging
Vivek Gupta, Ankit Saw, Pegah Nokhiz +3
Simple weighted averaging of word vectors often yields effective representations for sentences which outperform sophisticated seq2seq neural models in many tasks. While it is desir…