Selective Probabilistic Classifier Based on Hypothesis Testing

Saeed Bakhshi Germi, Esa Rahtu, Heikki Huttunen

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

1 Sitaatiot (Scopus)
7 Lataukset (Pure)

Abstrakti

In this paper, we propose a simple yet effective method to deal with the violation of the Closed-World Assumption for a classifier. Previous works tend to apply a threshold either on the classification scores or the loss function to reject the inputs that violate the assumption. However, these methods cannot achieve the low False Positive Ratio (FPR) required in safety applications. The proposed method is a rejection option based on hypothesis testing with probabilistic networks. With probabilistic networks, it is possible to estimate the distribution of outcomes instead of a single output. By utilizing Z-Test over the mean and standard deviation for each class, the proposed method can estimate the statistical significance of the network certainty and reject uncertain outputs. The proposed method was experimented on with different configurations of the COCO and CIFAR datasets. The performance of the proposed method is compared with the Softmax Response, which is a known top-performing method. It is shown that the proposed method can achieve a broader range of operation and cover a lower FPR than the alternative.

AlkuperäiskieliEnglanti
OtsikkoProceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021
ToimittajatA. Beghdadi, F. Alaya Cheikh, J.M.R.S. Tavares, A. Mokraoui, G. Valenzise, L. Oudre, M.A. Qureshi
KustantajaIEEE
Sivumäärä6
ISBN (elektroninen)9781665432306
ISBN (painettu)9781665432313
DOI - pysyväislinkit
TilaJulkaistu - 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaEuropean Workshop on Visual Information Processing - Paris, Ranska
Kesto: 23 kesäk. 202125 kesäk. 2021

Julkaisusarja

NimiEuropean Workshop on Visual Information Processing
ISSN (painettu)2164-974X
ISSN (elektroninen)2471-8963

Conference

ConferenceEuropean Workshop on Visual Information Processing
Maa/AlueRanska
KaupunkiParis
Ajanjakso23/06/2125/06/21

Julkaisufoorumi-taso

  • Jufo-taso 1

!!ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Information Systems
  • Signal Processing

Sormenjälki

Sukella tutkimusaiheisiin 'Selective Probabilistic Classifier Based on Hypothesis Testing'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä