Please use this identifier to cite or link to this item:
|Title:||Content-dependency reduction with multi-task learning in blind stitched panoramic image quality assessment||Authors:||Hou, Jingwen
|Keywords:||Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision||Issue Date:||2020||Source:||Hou, J., Lin, W., & Zhao, B. (2020). Content-dependency reduction with multi-task learning in blind stitched panoramic image quality assessment. Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP). doi:10.1109/ICIP40778.2020.9191241||Abstract:||In this work, we investigate deep learning based solutions to blind quality assessment of stitched panoramic images (SPI). The main problem to tackle is that the ground truth data is usually insufficient. As a result, the learned model can easily overfit data with specific content. Because most distortions of SPIs lie within local regions, the problem cannot be alleviated by commonly-used patch-wise training, which assumes local quality equals global quality. We propose a multi-task learning strategy which encourages learned representation to be less dependent on image content. A siamese network with two weight-shared CNN branches is trained to simultaneously compare the quality of two images of the same scene and predict the quality score of each image. Since two images of the same scene are processed by the same CNN, the CNN tends to find their quality differences instead of content differences under the constraint of the quality ranking objective. Because two tasks share the same representations learned by the CNN, the regression task can be further benefited from the quality-sensitive representations. Extensive experiments demonstrate the effectiveness of the proposed model and its superiority over existing SPI quality assessment methods.||URI:||https://hdl.handle.net/10356/144376||DOI:||10.1109/ICIP40778.2020.9191241||Rights:||© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work is available at: https://doi.org/10.1109/ICIP40778.2020.9191241||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||SCSE Conference Papers|
Updated on Jan 25, 2021
Updated on Jan 25, 2021
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.