Please use this identifier to cite or link to this item:
|Title:||The spatially-correlative loss for various image translation tasks||Authors:||Zheng, Chuanxia
|Keywords:||Engineering::Computer science and engineering::Computing methodologies::Pattern recognition||Issue Date:||2021||Source:||Zheng, C., Cham, T. & Cai, J. (2021). The spatially-correlative loss for various image translation tasks. IEEE Conference on Computer Vision and Pattern Recognition.||Abstract:||We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency while supporting large appearance changes during unpaired image-to-image (I2I) translation. Previous methods attempt this by using pixel-level cycle-consistency or feature-level matching losses, but the domain-specific nature of these losses hinder translation across large domain gaps. To address this, we exploit the spatial patterns of self-similarity as a means of defining scene structure. Our spatially-correlative loss is geared towards only capturing spatial relationships within an image rather than domain appearance. We also introduce a new self-supervised learning method to explicitly learn spatially-correlative maps for each specific translation task. We show distinct improvement over baseline models in all three modes of unpaired I2I translation: single-modal, multi-modal, and even single-image translation. This new loss can easily be integrated into existing network architectures and thus allows wide applicability.||URI:||https://hdl.handle.net/10356/151225||Rights:||© 2021 Institute of Electrical and Electronics Engineers (IEEE). All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||SCSE Conference Papers|
Updated on Jun 23, 2021
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.