Purchase this article with an account.
Philipp Grüning, Thomas Martinetz, Erhardt Barth; FP-nets as novel deep networks inspired by vision. Journal of Vision 2022;22(1):8. https://doi.org/10.1167/jov.22.1.8.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
Feature-product networks (FP-nets) are inspired by end-stopped cortical cells with FP-units that multiply the outputs of two filters. We enhance state-of-the-art deep networks, such as the ResNet and MobileNet, with FP-units and show that the resulting FP-nets perform better on the Cifar-10 and ImageNet benchmarks. Moreover, we analyze the hyperselectivity of the FP-net model neurons and show that this property makes FP-nets less sensitive to adversarial attacks and JPEG artifacts. We then show that the learned model neurons are end-stopped to different degrees and that they provide sparse representations with an entropy that decreases with hyperselectivity.
This PDF is available to Subscribers Only