Improving CNN classifiers by estimating test-time priors

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00337392" target="_blank" >RIV/68407700:21230/19:00337392 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/ICCVW.2019.00402" target="_blank" >https://doi.org/10.1109/ICCVW.2019.00402</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCVW.2019.00402" target="_blank" >10.1109/ICCVW.2019.00402</a>

Result language

angličtina

Original language name

Improving CNN classifiers by estimating test-time priors

Original language description

The problem of different training and test set class priors is addressed in the context of CNN classifiers. We compare two approaches to the estimation of the unknown test priors: an existing Maximum Likelihood Estimation (MLE) method and a proposed Maximum a Posteriori (MAP) approach introducing a Dirichlet hyper-prior on the class prior probabilities. Experimental results show a significant improvement in the fine-grained classification tasks using known evaluation-time priors, increasing top-1 accuracy by 4.0%on the FGVC iNaturalist 2018 validation set and by 3.9%on the FGVCx Fungi 2018 validation set. Estimation ofthe unknown test set priors noticeably increases the accuracy on the PlantCLEF dataset, allowing a single CNNmodel to achieve state-of-the-art results and to outperform the competition-winning ensemble of 12 CNNs. The pro-posed MAP estimation increases the prediction accuracy by2.8% on PlantCLEF 2017 and by 1.8% on FGVCx Fungi,where the MLE method decreases accuracy.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/TE01020415" target="_blank" >TE01020415: V3C - Visual Computing Competence Center</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2019

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

2019 IEEE International Conference on Computer Vision Workshops (ICCVW 2019)

ISBN

—

ISSN

2473-9944

e-ISSN

2473-9944

Number of pages

7

Pages from-to

3220-3226

Publisher name

IEEE Computer Society

Place of publication

Los Alamitos

Event location

Seoul

Event date

Oct 27, 2019

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—