Robust Multi-label Active Learning for Missing Labels

Bachelor Thesis (2021)
Author(s)

J. Rozen (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Lydia Chen – Mentor (TU Delft - Data-Intensive Systems)

T. Younesian – Graduation committee member (TU Delft - Data-Intensive Systems)

S. Ghiassi – Graduation committee member (TU Delft - Data-Intensive Systems)

F.A. Kuipers – Coach (TU Delft - Embedded Systems)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2021 Jonathan Rozen
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 Jonathan Rozen
Graduation Date
02-07-2021
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
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

Multi-label classification has gained a lot of attraction in the field of computer vision over the past couple of years. Here, each instance belongs to multiple class labels simultaneously. There are numerous methods for Multi-label classification, however all of them make the assumption that either the training images are completely labelled or that label correlations are given. Since Active Learning is frequently used when not much data is available, it could be used to determine the missing labels by querying an oracle. This paper proposes a novel solution that combines the current state-of-the-art for Multi-label classification with Active Learning to infer the missing labels. This is done with sampling strategies that try to select the most informative sample from the dataset by exploring the amount of missing labels. With these strategies, we try to minimize the relabeling cost for all samples, while maximizing the information gained. The chosen method called Hard sampling with entropy then looks to select those samples that both the model and we find informative. The chosen measure along with the other measure are then explored and evaluated on a subset of the MSCOCO dataset on 20%, 40% and 60% noise. Hard sampling with entropy then outperforms the state-of-the-art by more then 30%, as well as the baseline sampling method by 2% for 60% noise.

Files

License info not available