Salvato in:
Dettagli Bibliografici
Autori principali: Kisel, Nikita, Volkov, Illia, Hanzelkova, Katerina, Janouskova, Klara, Matas, Jiri
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.00076
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916500735000576
author Kisel, Nikita
Volkov, Illia
Hanzelkova, Katerina
Janouskova, Klara
Matas, Jiri
author_facet Kisel, Nikita
Volkov, Illia
Hanzelkova, Katerina
Janouskova, Klara
Matas, Jiri
contents Since its release, ImageNet-1k dataset has become a gold standard for evaluating model performance. It has served as the foundation for numerous other datasets and training tasks in computer vision. As models have improved in accuracy, issues related to label correctness have become increasingly apparent. In this blog post, we analyze the issues in the ImageNet-1k dataset, including incorrect labels, overlapping or ambiguous class definitions, training-evaluation domain shifts, and image duplicates. The solutions for some problems are straightforward. For others, we hope to start a broader conversation about refining this influential dataset to better serve future research.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00076
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Flaws of ImageNet, Computer Vision's Favourite Dataset
Kisel, Nikita
Volkov, Illia
Hanzelkova, Katerina
Janouskova, Klara
Matas, Jiri
Computer Vision and Pattern Recognition
Since its release, ImageNet-1k dataset has become a gold standard for evaluating model performance. It has served as the foundation for numerous other datasets and training tasks in computer vision. As models have improved in accuracy, issues related to label correctness have become increasingly apparent. In this blog post, we analyze the issues in the ImageNet-1k dataset, including incorrect labels, overlapping or ambiguous class definitions, training-evaluation domain shifts, and image duplicates. The solutions for some problems are straightforward. For others, we hope to start a broader conversation about refining this influential dataset to better serve future research.
title Flaws of ImageNet, Computer Vision's Favourite Dataset
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.00076