Search Results for author: Shaunak Halbe

Found 4 papers, 1 papers with code

HePCo: Data-Free Heterogeneous Prompt Consolidation for Continual Federated Learning

no code implementations16 Jun 2023 Shaunak Halbe, James Seale Smith, Junjiao Tian, Zsolt Kira

In this paper, we attempt to tackle forgetting and heterogeneity while minimizing overhead costs and without requiring access to any stored data.

Federated Learning Image Classification

A Closer Look at Rehearsal-Free Continual Learning

no code implementations31 Mar 2022 James Seale Smith, Junjiao Tian, Shaunak Halbe, Yen-Chang Hsu, Zsolt Kira

Next, we explore how to leverage knowledge from a pre-trained model in rehearsal-free continual learning and find that vanilla L2 parameter regularization outperforms EWC parameter regularization and feature distillation.

Continual Learning Knowledge Distillation +2

Robustness through Data Augmentation Loss Consistency

1 code implementation21 Oct 2021 Tianjian Huang, Shaunak Halbe, Chinnadhurai Sankar, Pooyan Amini, Satwik Kottur, Alborz Geramifard, Meisam Razaviyayn, Ahmad Beirami

Our experiments show that DAIR consistently outperforms ERM and DA-ERM with little marginal computational cost and sets new state-of-the-art results in several benchmarks involving covariant data augmentation.

Multi-domain Dialogue State Tracking Visual Question Answering

Exploring Weaknesses of VQA Models through Attribution Driven Insights

no code implementations WS 2020 Shaunak Halbe

Deep Neural Networks have been successfully used for the task of Visual Question Answering for the past few years owing to the availability of relevant large scale datasets.

Question Answering Visual Question Answering

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