Self-Supervised Few Shot Learning

Prototypical Contrastive Learning with Graphs

Master Thesis (2022)
Author(s)

O.K. Shirekar (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

H Jamali Rad – Mentor (TU Delft - Pattern Recognition and Bioinformatics)

Jan van Gemert – Graduation committee member (TU Delft - Pattern Recognition and Bioinformatics)

E. Isufi – Graduation committee member (TU Delft - Multimedia Computing)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2022 Ojas Shirekar
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 Ojas Shirekar
Graduation Date
31-08-2022
Awarding Institution
Delft University of Technology
Programme
['Computer Science']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

A primary trait of humans is the ability to learn rich representations and relationships between entities from just a handful of examples without much guidance. Unsupervised few-shot learning is an undertaking aimed at reducing this fundamental gap between smart human adaptability and machines. We present a contrastive learning scheme for unsupervised few-shot classification, where we supplement a convolutional network’s strong inductive prior with a self-attention based message passing neural network to exploit intra-batch relations between images. We also show that an optimal-transport (OT) based task-awareness algorithm generates task-representative prototypes that lead to more accurate classification and aid in elevating the robustness of pre-trained models. We show that our approach (SAMPTransfer) offers appreciable performance improvements over its competitors in both in/cross-domain few shot classification scenarios, setting new standards in the miniImagenet, tieredImagenet and CDFSL benchmarks.

Files

Thesis_Main.pdf
(pdf | 40.2 Mb)
License info not available