Learning multi-instance sub-pixel point localization

Schroeter, Julien, Sidorov, Kirill ORCID: https://orcid.org/0000-0001-7935-4132 and Marshall, Andrew ORCID: https://orcid.org/0000-0003-2789-1395 2021. Learning multi-instance sub-pixel point localization. Presented at: 15th Asian Conference on Computer Vision (ACCV 2020), Virtual (Kyoto), 30 November - 4 December 2020. Published in: Ishikawa, H., Liu, CL., Pajdla, T. and Shi, J. eds. Proceedings of Computer Vision – ACCV 2020. Springer, pp. 669-686. 10.1007/978-3-030-69541-5_40 Item availability restricted.

PDF - Accepted Post-Print Version Restricted to Repository staff only Download (1MB)

Abstract

In this work, we propose a novel approach that allows for the end-to-end learning of multi-instance point detection with inherent sub-pixel precision capabilities. To infer unambiguous localization estimates, our model relies on three components: the continuous prediction capabilities of offset-regression-based models, the finer-grained spatial learning ability of a novel continuous heatmap matching loss function introduced to that effect, and the prediction sparsity ability of count-based regularization. We demonstrate strong sub-pixel localization accuracy on single molecule localization microscopy and checkerboard corner detection, and improved sub-frame event detection performance in sport videos.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Professional Services > Advanced Research Computing @ Cardiff (ARCCA) Schools > Computer Science & Informatics
Publisher:	Springer
ISBN:	978-3-030-69540-8
Date of First Compliant Deposit:	14 December 2020
Date of Acceptance:	16 September 2020
Last Modified:	31 Jul 2025 11:13
URI:	https://orca.cardiff.ac.uk/id/eprint/136988

Actions (repository staff only)

Edit Item