Self-supervised Learning Aided Blind Stitched Panoramic Image Quality Assessment

Jui Hsiu Chiang, Chih Wei Tang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

For deep learning based stitched panoramic image quality assessment, it is costly to train a network model using a large-scale dataset with human annotation. Moreover, it is practical to evaluate image quality without reference images (i.e., Blind Stitched Image Quality Assessment, BSIQA). Selfsupervised learning (SSL) avoids the use of annotated large-scale training dataset while few BSIQA schemes of panoramic stitched images using SSL have been proposed. Thus this paper proposes a SSL aided BSIQA scheme for panoramas. The first training phase learns from a large-scale dataset, where SSL based image colorization is incorporated into supervised learning based classification for learning generalized visual representations. With transferred knowledge from the first phase, the second training phase learns from a small dataset with subjective scores for the task of BSIQA. Test results show that SSL indeed improves prediction accuracy of BSIQA of panoramas on ISIQA dataset.

原文???core.languages.en_GB???
主出版物標題2021 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665433280
DOIs
出版狀態已出版 - 2021
事件8th IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021 - Penghu, Taiwan
持續時間: 15 9月 202117 9月 2021

出版系列

名字2021 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???8th IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021
國家/地區Taiwan
城市Penghu
期間15/09/2117/09/21

指紋

深入研究「Self-supervised Learning Aided Blind Stitched Panoramic Image Quality Assessment」主題。共同形成了獨特的指紋。

引用此