Welcome!
Thanks for visiting my website!
I am a PhD Student (Pre-doctoral Researcher) at the Computer Vision Center, Universitat Autonoma de Barcelona working with Dr. Bartlomiej Twardowski and Dr. Joost van de Weijer at the Learning and Machine Perception (LAMP) group. I am working on Continual Learning problems.
I graduated with a B.E. in Computer Science and M.Sc. in Mathematics from Birla Institute of Technology and Science, Pilani, India in 2022.
My research interests include:
Continual Learning (Image classification, Semantic segmentation, Object detection, Test-time adaptation)
Federated Learning
Data-efficient and Label-efficient Learning
Transfer Learning
Domain Adaptation
I reviewed papers in CVPR 2024, ECCV 2024, WACV 2024, BMVC 2024 as well as in Journals (TIP, TNNLS).
NeurIPS 2023
ICCV 2023
Recent News!
March 2024: Our recent work 'Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers' has been accepted at the CLVision workshop in CVPR 2024. (Paper) (Code)
Feb 2024: Our paper 'Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning' has been accepted at the Conference on Computer Vision and Pattern Recognition (CVPR) 2024. (Paper) (Code).
2023 ->
Dec 2023: Attended the Deep Learning Barcelona Symposium (DLBCN) 2023 and presented our NeurIPS paper. (Video)
Dec 2023: Attended the Conference on Neural Information Processing Systems (NeurIPS 2023) in New Orleans, USA.
Presented the poster of our paper 'FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning'.
Oct 2023: Attended the International Conference on Computer Vision (ICCV) 2023 in Paris.
Gave an oral presentation of our solution for the 'Continual Test-time Adaptation for Semantic Segmentation' challenge at the Visual Continual Learning Workshop.
Presented the poster of our paper 'Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection'.
Sept 2023: The first paper from my PhD, 'FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning' has been accepted at the 37th Conference on Neural Information Processing Systems (NeurIPS 2023). [Code]
Sept 2023: Our team 'Continual Learners' won the innovation award in the 'Continual Test-time Adaptation for Semantic Segmentation and Object Detection' challenge at the Visual Continual Learning Workshop at ICCV 2023. [Technical Report]
July 2023: Our paper 'Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection' is accepted at the International Conference on Computer Vision (ICCV) 2023.
June 2023: Attended the Generative Modeling Summer School (GeMSS) in Copenhagen.
March 2023: Joined Computer Vision Center (CVC) Barcelona as a pre-doctoral researcher. Started my PhD in Computer Science at the Universitat Autonoma de Barcelona. Research on Continual Learning under the supervision of Dr. Joost van de Weijer and Dr. Bartlomiej Twardowski.
January 2023: A new paper 'Bounding Box Priors for Cell Detection with Point Annotations' is accepted at the International Symposium of Biomedical Imaging (ISBI) 2023.
2022 ->
October 2022: Our paper 'Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation' is accepted at the IEEE Winter Conference on Applications of Computer Vision (WACV) 2023.
September 2022: Joined Computer Vision Center (CVC) Barcelona as a research assistant. Research on Continual Few-shot Learning and Continual Object Detection under the supervision of Dr. Joost van de Weijer at the Learning and Machine Perception (LAMP) group.
July 2022: Graduated from BITS Pilani, India with an M.Sc. in Mathematics and a B.E. in Computer Science.
February 2022: Joined DFKI (German Research Center for Artificial Intelligence), Kaiserslautern as a research assistant. Research on Incremental Learning for Semantic Segmentation under the supervision of Prof. Dr. Didier Stricker at the Augmented Vision Department.
August 2021: Our paper on 'Graph-based Approach for Enumerating Floorplans Based on Users Specifications' is accepted at AIEDAM Journal (Cambridge University Press). Work done under the supervision of Dr. Krishnendra Shekhawat at BITS Pilani.