Learning Multi-Instance Sub-pixel Point Localization

Julien Schroeter, Tinne Tuytelaars, Kirill Sidorov, David Marshall; Proceedings of the Asian Conference on Computer Vision (ACCV), 2020


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.

Related Material

[pdf] [supp] [code]
@InProceedings{Schroeter_2020_ACCV, author = {Schroeter, Julien and Tuytelaars, Tinne and Sidorov, Kirill and Marshall, David}, title = {Learning Multi-Instance Sub-pixel Point Localization}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {November}, year = {2020} }