Mattia Litrico
Semi-Supervised Domain Adaptation for Holistic Counting under Label Gap
Litrico, Mattia; Battiato, Sebastiano; Tsaftaris, Sotirios A.; Giuffrida, Mario Valerio
Authors
Sebastiano Battiato
Sotirios A. Tsaftaris
Mario Valerio Giuffrida
Abstract
This paper proposes a novel approach for semi-supervised domain adaptation for holistic regression tasks, where a DNN predicts a continuous value y∈R given an input image x. The current literature generally lacks specific domain adaptation approaches for this task, as most of them mostly focus on classification. In the context of holistic regression, most of the real-world datasets not only exhibit a covariate (or domain) shift, but also a label gap—the target dataset may contain labels not included in the source dataset (and vice versa). We propose an approach tackling both covariate and label gap in a unified training framework. Specifically, a Generative Adversarial Network (GAN) is used to reduce covariate shift, and label gap is mitigated via label normalisation. To avoid overfitting, we propose a stopping criterion that simultaneously takes advantage of the Maximum Mean Discrepancy and the GAN Global Optimality condition. To restore the original label range—that was previously normalised—a handful of annotated images from the target domain are used. Our experimental results, run on 3 different datasets, demonstrate that our approach drastically outperforms the state-of-the-art across the board. Specifically, for the cell counting problem, the mean squared error (MSE) is reduced from 759 to 5.62; in the case of the pedestrian dataset, our approach lowered the MSE from 131 to 1.47. For the last experimental setup, we borrowed a task from plant biology, i.e., counting the number of leaves in a plant, and we ran two series of experiments, showing the MSE is reduced from 2.36 to 0.88 (intra-species), and from 1.48 to 0.6 (inter-species).
Citation
Litrico, M., Battiato, S., Tsaftaris, S. A., & Giuffrida, M. V. (2021). Semi-Supervised Domain Adaptation for Holistic Counting under Label Gap. Journal of Imaging, 7(10), Article 198. https://doi.org/10.3390/jimaging7100198
Journal Article Type | Article |
---|---|
Acceptance Date | Sep 21, 2021 |
Online Publication Date | Sep 29, 2021 |
Publication Date | 2021 |
Deposit Date | Nov 11, 2021 |
Publicly Available Date | Nov 11, 2021 |
Journal | Journal of Imaging |
Print ISSN | 2313-433X |
Publisher | MDPI |
Peer Reviewed | Peer Reviewed |
Volume | 7 |
Issue | 10 |
Article Number | 198 |
DOI | https://doi.org/10.3390/jimaging7100198 |
Keywords | domain adaptation; holistic counting; regression; label gap |
Public URL | http://researchrepository.napier.ac.uk/Output/2820679 |
Files
Semi-Supervised Domain Adaptation for Holistic Counting under Label Gap
(1.2 Mb)
PDF
Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/
Copyright Statement
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
You might also like
Editorial: Synthetic data for computer vision in agriculture
(2023)
Journal Article
Editorial: Computer vision in plant phenotyping and agriculture
(2023)
Journal Article
An omnidirectional approach to touch-based continuous authentication
(2023)
Journal Article
CAPE: Context-Aware Private Embeddings for Private Language Learning
(2021)
Conference Proceeding
Downloadable Citations
About Edinburgh Napier Research Repository
Administrator e-mail: repository@napier.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search