Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks

Min-Nets are inspired by end-stopped cortical cells with units that output the minimum of two learned filters. We insert such Min-units into state-of-the-art deep networks, such as the popular ResNet and DenseNet, and show that the resulting Min-Nets perform better on the Cifar-10 benchmark. Moreove...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-01
Main Authors: Grüning, Philipp, Erhardt Barth
Format: Article
Language:English
Subjects:
Image compression
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Min-Nets are inspired by end-stopped cortical cells with units that output the minimum of two learned filters. We insert such Min-units into state-of-the-art deep networks, such as the popular ResNet and DenseNet, and show that the resulting Min-Nets perform better on the Cifar-10 benchmark. Moreover, we show that Min-Nets are more robust against JPEG compression artifacts. We argue that the minimum operation is the simplest way of implementing an AND operation on pairs of filters and that such AND operations introduce a bias that is appropriate given the statistics of natural images.
ISSN:2331-8422