Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 17 of 3320
Back to Result List

Improving Stability during Upsampling – on the Importance of Spatial Context

  • State-of-the-art models for pixel-wise prediction tasks such as image restoration, image segmentation, or disparity estimation, involve several stages of data resampling, in which the resolution of feature maps is first reduced to aggregate information and then sequentially increased to generate a high-resolution output. Several previous works have investigated the effect of artifacts that areState-of-the-art models for pixel-wise prediction tasks such as image restoration, image segmentation, or disparity estimation, involve several stages of data resampling, in which the resolution of feature maps is first reduced to aggregate information and then sequentially increased to generate a high-resolution output. Several previous works have investigated the effect of artifacts that are invoked during downsampling and diverse cures have been proposed that facilitate to improve prediction stability and even robustness for image classification. However, equally relevant, artifacts that arise during upsampling have been less discussed. This is significantly relevant as upsampling and downsampling approaches face fundamentally different challenges. While during downsampling, aliases and artifacts can be reduced by blurring feature maps, the emergence of fine details is crucial during upsampling. Blurring is therefore not an option and dedicated operations need to be considered. In this work, we are the first to explore the relevance of context during upsampling by employing convolutional upsampling operations with increasing kernel size while keeping the encoder unchanged. We find that increased kernel sizes can in general improve the prediction stability in tasks such as image restoration or image segmentation, while a block that allows for a combination of small-size kernels for fine details and large-size kernels for artifact removal and increased context yields the best results.show moreshow less

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Document Type:Article (unreviewed)
Zitierlink: https://opus.hs-offenburg.de/8402
Bibliografische Angaben
Title (English):Improving Stability during Upsampling – on the Importance of Spatial Context
Author:Shashank Agnihotri, Julia GrabinskiStaff MemberORCiD, Margret Keuper
Year of Publication:2023
First Page:1
Last Page:24
DOI:https://doi.org/10.48550/arXiv.2311.17524
Language:English
Inhaltliche Informationen
Institutes:Forschung / IMLA - Institute for Machine Learning and Analytics
Institutes:Bibliografie
Formale Angaben
Relevance:Wiss. Zeitschriftenartikel unreviewed
Open Access: Open Access 
 Diamond 
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International
ArXiv Id:http://arxiv.org/abs/2311.17524