Vinay Kumar Verma
Currently, I am a Post Doctoral fellow under the guidance of Prof. Carin at Duke University in the Department of Electrical and Computer Engineering.
Before joining Duke I was a Ph. D. scholar at the Department of Computer Science and Engineering, IIT Kanpur. In Ph. D. I worked under the guidance of Dr Piyush Rai. In my Ph. D. I have worked on Zero-Shot Learning, Multi-label Zero-shot Learning and Deep Model Compression.
My interest in research also includes Probabilistic Machine Learning, Deep Learning, Continual Learning, Few-Shot Learning and Computer Vision. More about me can be found in the CV.
Google Scholar (Please refer to this for the recent publication)
Recent News
Paper on title "CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks", accepted to NeurIPS-21.
Paper on title "Hypernetworks for Continual Semi-Supervised Learning" accepted to CSSL-IJCAI-2021. (Best Student Paper Award)
Paper on title "Knowledge Consolidation based Class Incremental Online Learning with Limited Data" accepted to IJCAI-2021.
Paper on title "Efficient Feature Transformations for Discriminative and Generative Incremental Learning" accepted to CVPR-2021.
Paper on title "Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors" accepted to AISTATS-2021.
Received the Outstanding PhD Thesis Award from the IIT Kanpur.
Paper on title Towards Zero-Shot Learning with Fewer Seen Class Examples accepted to WACV-2021,
Paper on title Calibrating CNNs for Lifelong Learning accepted to NeurIPS-2020,
Successfully defended my PhD on 2 Sep 2020.
Joined Post-Doc under the guidance of Prof. Carin at Duke University.
Four paper accepted WACV-2020.
Paper on title A Generative Framework for Zero-Shot Learning with Adversarial Domain Adaptation accepted to WACV-2020,
Paper on title Adversarial Joint-Distribution Learning for Novel Class Sketch-Based Image Retrieval accepted to ICCVW-2019,
Aug 7, 2019: Presenting our work on "deep model compression" to IJCAI-19.