Metraipolis › archive › dc_683d427fa5e9

Are open set classification methods effective on large-scale datasets? — Europe PMC PMID:32886692

Source
Europe PMC (en)
Original
https://europepmc.org/article/MED/32886692
DOI
10.1371/journal.pone.0238302
License (as archived)
CC0-1.0
Archived
2026-11-07T14:36:31.309Z
SHA-256 of the archived text
dc7eb6773a294a57fd22dc1af5f1445348e5ddf21280a3d96f4ecfd165b1895b
Stable URL of this page
https://metraipolis.com/documento/dc_683d427fa5e9

How to cite

Are open set classification methods effective on large-scale datasets? — Europe PMC PMID:32886692 — Europe PMC (en), https://europepmc.org/article/MED/32886692 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_683d427fa5e9 (Metraipolis archive dc_683d427fa5e9, sha256 dc7eb6773a294a57fd22dc1af5f1445348e5ddf21280a3d96f4ecfd165b1895b)
BibTeX
@misc{dc683d427fa5e9,
  title = {Are open set classification methods effective on large-scale datasets? — Europe PMC PMID:32886692},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/32886692},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_683d427fa5e9; sha256 dc7eb6773a294a57fd22dc1af5f1445348e5ddf21280a3d96f4ecfd165b1895b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/32886692. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Supervised classification methods often assume the train and test data distributions are the same and that all classes in the test set are present in the training set. However, deployed classifiers often require the ability to recognize inputs from outside the training set as unknowns. This problem has been studied under multiple paradigms including out-of-distribution detection and open set recognition. For convolutional neural networks, there have been two major approaches: 1) inference methods to separate knowns from unknowns and 2) feature space regularization strategies to improve model robustness to novel inputs. Up to this point, there has been little attention to exploring the relationship between the two approaches and directly comparing performance on large-scale datasets that have more than a few dozen categories. Using the ImageNet ILSVRC-2012 large-scale classification dataset, we identify novel combinations of regularization and specialized inference methods that perform best across multiple open set classification problems of increasing difficulty level. We find that input perturbation and temperature scaling yield significantly better performance on large-scale datasets than other inference methods tested, regardless of the feature space regularization strategy. Conversely, we find that improving performance with advanced regularization schemes during training yields better performance when baseline inference techniques are used; however, when advanced inference methods are used to detect open set classes, the utility of these combersome training paradigms is less evident.

Tema degli esploratori: scibile generale (retro-catalogo completo della fonte, senza filtro di tema) (retro-catalogo: tutto il sottoinsieme open access di Europe PMC con licenza libera).
Pubblicazione: PloS one, 2020 (prima pubblicazione 2020-09-04).
Identificativi: PMID 32886692 · PMCID PMC7473573 · DOI 10.1371/journal.pone.0238302.
Descrittori MeSH principali: Algorithms; Neural Networks, Computer.
Pagina: https://europepmc.org/article/MED/32886692 — https://doi.org/10.1371/journal.pone.0238302. Autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza dell'articolo dichiarata da Europe PMC: CC0 (la versione è indicata dall'editore sulla pagina). Abstract riportato senza modifiche al contenuto, con attribuzione; deposito marcato CC0.
Letto il 2026-11-07T14:31:45.174Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.