arXiv Open Access 2025

Orientation Scores should be a Piece of Cake

Finn M. Sherry Chase van de Geijn Erik J. Bekkers Remco Duits
Lihat Sumber

Abstrak

We axiomatically derive a family of wavelets for an orientation score, lifting from position space $\mathbb{R}^2$ to position and orientation space $\mathbb{R}^2\times S^1$, with fast reconstruction property, that minimise position-orientation uncertainty. We subsequently show that these minimum uncertainty states are well-approximated by cake wavelets: for standard parameters, the uncertainty gap of cake wavelets is less than 1.1, and in the limit, we prove the uncertainty gap tends to the minimum of 1. Next, we complete a previous theoretical argument that one does not have to train the lifting layer in (PDE-)G-CNNs, but can instead use cake wavelets. Finally, we show experimentally that in this way we can reduce the network complexity and improve the interpretability of (PDE-)G-CNNs, with only a slight impact on the model's performance.

Topik & Kata Kunci

Penulis (4)

F

Finn M. Sherry

C

Chase van de Geijn

E

Erik J. Bekkers

R

Remco Duits

Format Sitasi

Sherry, F.M., Geijn, C.v.d., Bekkers, E.J., Duits, R. (2025). Orientation Scores should be a Piece of Cake. https://arxiv.org/abs/2504.00702

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓