Carregant...
Miniatura

Tipus de document

Article

Versió

Versió publicada

Data de publicació

Llicència de publicació

cc-by (c) Mena, José et al., 2020
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/168537

Uncertainty-based Rejection Wrappers for Black-box Classifiers

Títol de la revista

Director/Tutor

ISSN de la revista

Títol del volum

Resum

Machine Learning as a Service platform is a very sensible choice for practitioners that wantto incorporate machine learning to their products while reducing times and costs. However, to benefit theiradvantages, a method for assessing their performance when applied to a target application is needed. In thiswork, we present a robust uncertainty-based method for evaluating the performance of both probabilistic andcategorical classification black-box models, in particular APIs, that enriches the predictions obtained withan uncertainty score. This uncertainty score enables the detection of inputs with very confident but erroneouspredictions while protecting against out of distribution data points when deploying the model in a productivesetting. We validate the proposal in different natural language processing and computer vision scenarios.Moreover, taking advantage of the computed uncertainty score, we show that one can significantly increasethe robustness and performance of the resulting classification system by rejecting uncertain predictions

Citació

Citació

MENA, José, PUJOL VILA, Oriol, VITRIÀ I MARCA, Jordi. Uncertainty-based Rejection Wrappers for Black-box Classifiers. _IEEE Access_. 2020. Vol. 8, núm. 101721-101746. [consulta: 13 de gener de 2026]. ISSN: 2169-3536. [Disponible a: https://hdl.handle.net/2445/168537]

Exportar metadades

JSON - METS

Compartir registre