Schroeter, Julien, Sidorov, Kirill ![]() ![]() 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 |