Show simple item record

dc.contributor.authorMyburgh, Johannes C.
dc.contributor.authorMouton, Coenraad
dc.contributor.authorDavel, Marelie H.
dc.date.accessioned2021-04-14T08:58:05Z
dc.date.available2021-04-14T08:58:05Z
dc.date.issued2020
dc.identifier.isbn978-3-030-66151-9
dc.identifier.issn1865-0929
dc.identifier.urihttp://hdl.handle.net/10394/36935
dc.identifier.urihttps://doi.org/10.1007/978-3-030-66151-9_18
dc.identifier.urihttps://arxiv.org/abs/2104.05997
dc.description.abstractAlthough Convolutional Neural Networks (CNNs) are widely used, their translation invariance (ability to deal with translated inputs) is still subject to some controversy. We explore this question using translation-sensitivity maps to quantify how sensitive a standard CNN is to a translated input. We propose the use of cosine similarity as sensitivity metric over Euclidean distance, and discuss the importance of restricting the dimensionality of either of these metrics when comparing architectures. Our main focus is to investigate the effect of different architectural components of a standard CNN on that network’s sensitivity to translation. By varying convolutional kernel sizes and amounts of zero padding, we control the size of the feature maps produced, allowing us to quantify the extent to which these elements influence translation invariance. We also measure translation invariance at different locations within the CNN to determine the extent to which convolutional and fully connected layers, respectively, contribute to the translation invariance of a CNN as a whole. Our analysis indicates that both convolutional kernel size and feature map size have a systematic influence on translation invariance. We also see that convolutional layers contribute less than expected to translation invariance, when not specifically forced to do so.en_US
dc.language.isoenen_US
dc.publisherSouthern African Conference for Artificial Intelligence Researchen_US
dc.subjectConvolutional Neural Networksen_US
dc.subjectTranslation Invarianceen_US
dc.subjectDeep Learningen_US
dc.titleTracking translation invariance in CNNsen_US
dc.typeArticleen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record