Cargando…
Critical analysis on the reproducibility of visual quality assessment using deep features
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...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9380959/ https://www.ncbi.nlm.nih.gov/pubmed/35972922 http://dx.doi.org/10.1371/journal.pone.0269715 |
_version_ | 1784768978356273152 |
---|---|
author | Götz-Hahn, Franz Hosu, Vlad Saupe, Dietmar |
author_facet | Götz-Hahn, Franz Hosu, Vlad Saupe, Dietmar |
author_sort | Götz-Hahn, Franz |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-9380959 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-93809592022-08-17 Critical analysis on the reproducibility of visual quality assessment using deep features Götz-Hahn, Franz Hosu, Vlad Saupe, Dietmar PLoS One Research Article 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. Public Library of Science 2022-08-16 /pmc/articles/PMC9380959/ /pubmed/35972922 http://dx.doi.org/10.1371/journal.pone.0269715 Text en © 2022 Götz-Hahn et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Götz-Hahn, Franz Hosu, Vlad Saupe, Dietmar Critical analysis on the reproducibility of visual quality assessment using deep features |
title | Critical analysis on the reproducibility of visual quality assessment using deep features |
title_full | Critical analysis on the reproducibility of visual quality assessment using deep features |
title_fullStr | Critical analysis on the reproducibility of visual quality assessment using deep features |
title_full_unstemmed | Critical analysis on the reproducibility of visual quality assessment using deep features |
title_short | Critical analysis on the reproducibility of visual quality assessment using deep features |
title_sort | critical analysis on the reproducibility of visual quality assessment using deep features |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9380959/ https://www.ncbi.nlm.nih.gov/pubmed/35972922 http://dx.doi.org/10.1371/journal.pone.0269715 |
work_keys_str_mv | AT gotzhahnfranz criticalanalysisonthereproducibilityofvisualqualityassessmentusingdeepfeatures AT hosuvlad criticalanalysisonthereproducibilityofvisualqualityassessmentusingdeepfeatures AT saupedietmar criticalanalysisonthereproducibilityofvisualqualityassessmentusingdeepfeatures |