Full metadata record
DC FieldValueLanguage
dc.contributor.authorWeber, Maurice-
dc.contributor.authorRenggli, Cedric-
dc.contributor.authorGrabner, Helmut-
dc.contributor.authorZhang, Ce-
dc.description.abstractDeep neural networks have recently advanced the state-of-the-art in image compression and surpassed many traditional compression algorithms. The training of such networks involves carefully trading off entropy of the latent representation against reconstruction quality. The term quality crucially depends on the observer of the images which, in the vast majority of literature, is assumed to be human. In this paper, we aim to go beyond this notion of compression quality and look at human visual perception and image classification simultaneously. To that end, we use a family of loss functions that allows to optimize deep image compression depending on the observer and to interpolate between human perceived visual quality and classification accuracy, enabling a more unified view on image compression. Our extensive experiments show that using perceptual loss functions to train a compression system preserves classification accuracy much better than traditional codecs such as BPG without requiring retraining of classifiers on compressed images. For example, compressing ImageNet to 0.25 bpp reduces Inception-ResNet classification accuracy by only 2%. At the same time, when using a human friendly loss function, the same compression system achieves competitive performance in terms of MS-SSIM. By combining these two objective functions, we show that there is a pronounced trade-off in compression quality between the human visual system and classification accuracy.de_CH
dc.rightsLicence according to publishing contractde_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.titleObserver dependent lossy image compressionde_CH
dc.typeKonferenz: Paperde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Datenanalyse und Prozessdesign (IDP)de_CH
zhaw.conference.details42nd German Conference on Pattern Recognition (DAGM-GCPR), virtual, 28 September - 1 October 2020de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.