Deep Shankar Pandey

I’m a 5th year Ph.D. Student in Computer Science working with Prof. Qi Yu at Machine Learning and Data Intensive Computing Lab, RIT. I completed my undergraduate in Electronics and Communication Engineering from Institute of Engineering, Pulchowk Campus, Nepal.

Research

I am interested in developing trustworthy deep learning models that can learn from limited data. My research focuses on developing computationally-efficient, adversarially robust, deep learning models with accurate fine-grained uncertainty quantification capabilities, with a special focus on meta-learning models. The developed models have been successfully used for improved few-shot classification, few-shot regression, and image completion problems.

My resume: Deep Resume, updated on October 14, 2023. My Research Publications: Publications List

Research Interests:

Uncertainty Awareness, Adversarial Robustness, Meta-Learning, Transfer Learning, Multi-task Learning, Few-Shot Learning, Pattern recognition, and application of Deep Learning to real-world problems

News

Aug 19, 2023	I have successfully completed summer internship as Deep Learning for Image and Video Processing Intern at InterDigital Communications.
Jul 26, 2023	Our paper titled Learn to Accumulate Evidence from All Training Samples: Theory and Practice is accepted at ICML 2023.
Jul 24, 2023	Our paper titled Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery is accepted at ICML 2023.
Feb 9, 2023	Our paper titled Evidential Conditional Neural Processes is accepted as a full paper with oral presentation at AAAI 2023.
Jun 19, 2022	Our paper titled Multidimensional Belief Quantification for Label-Efficient Meta-Learning is published at CVPR 2022

Selected Publications

CVPR 2022

Multidimensional Belief Quantification for Label-Efficient Meta-Learning

Deep Shankar Pandey, and Qi Yu

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jun 2022

Abs

Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few samples introduces uncertainty, and quantifying model confidence for few-shot predictions is essential for many critical domains. Furthermore, few-shot tasks used in meta training are usually sampled randomly from a task distribution for an iterative model update, leading to high labeling costs and computational overhead in meta-training. We propose a novel uncertainty-aware task selection model for label efficient meta-learning. The proposed model formulates a multidimensional belief measure, which can quantify the known uncertainty and lower bound the unknown uncertainty of any given task. Our theoretical result establishes an important relationship between the conflicting belief and the incorrect belief. The theoretical result allows us to estimate the total uncertainty of a task, which provides a principled criterion for task selection. A novel multi-query task formulation is further developed to improve both the computational and labeling efficiency of meta-learning. Experiments conducted over multiple real-world few-shot image classification tasks demonstrate the effectiveness of the proposed model.