Critical analysis on the reproducibility of visual quality assessment using deep features
Franz Götz-Hahn,
Vlad Hosu and
Dietmar Saupe
PLOS ONE, 2022, vol. 17, issue 8, 1-25
Abstract:
Data used to train supervised machine learning models are commonly split into independent training, validation, and test sets. This paper illustrates that complex data leakage cases have occurred in the no-reference image and video quality assessment literature. Recently, papers in several journals reported performance results well above the best in the field. However, our analysis shows that information from the test set was inappropriately used in the training process in different ways and that the claimed performance results cannot be achieved. When correcting for the data leakage, the performances of the approaches drop even below the state-of-the-art by a large margin. Additionally, we investigate end-to-end variations to the discussed approaches, which do not improve upon the original.
Date: 2022
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)
Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0269715 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 69715&type=printable (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0269715
DOI: 10.1371/journal.pone.0269715
Access Statistics for this article
More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().