Recognition of the Amazonian flora by Inception Networks with Test-time Class Prior Estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F19%3A43956403" target="_blank" >RIV/49777513:23520/19:43956403 - isvavai.cz</a>

Výsledek na webu

<a href="http://ceur-ws.org/Vol-2380/paper_108.pdf" target="_blank" >http://ceur-ws.org/Vol-2380/paper_108.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Recognition of the Amazonian flora by Inception Networks with Test-time Class Prior Estimation

Popis výsledku v původním jazyce

The paper describes an automatic system for recognition of 10,000 plant species, with focus on species from the Guiana shield and the Amazon rain forest. The proposed system achieves the best results on the PlantCLEF 2019 test set with 31.9% accuracy. Compared against human experts in plant recognition, the system performed better than 3 of the 5 participating human experts and achieved 41.0% accuracy on the subset for expert evaluation. The proposed system is based on the Inception-v4 and Inception-ResNet-v2 Convolutional Neural Network (CNN) architectures. Performance improvements were achieved by: adjusting the CNN predictions according to the estimated change of the class prior probabilities, replacing network parameters with their running averages, test-time data augmentation, filtering the provided training set and adding additional training images from GBIF.

Název v anglickém jazyce

Recognition of the Amazonian flora by Inception Networks with Test-time Class Prior Estimation

Popis výsledku anglicky

The paper describes an automatic system for recognition of 10,000 plant species, with focus on species from the Guiana shield and the Amazon rain forest. The proposed system achieves the best results on the PlantCLEF 2019 test set with 31.9% accuracy. Compared against human experts in plant recognition, the system performed better than 3 of the 5 participating human experts and achieved 41.0% accuracy on the subset for expert evaluation. The proposed system is based on the Inception-v4 and Inception-ResNet-v2 Convolutional Neural Network (CNN) architectures. Performance improvements were achieved by: adjusting the CNN predictions according to the estimated change of the class prior probabilities, replacing network parameters with their running averages, test-time data augmentation, filtering the provided training set and adding additional training images from GBIF.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

CEUR Workshop Proceedings Vol-2380

ISBN

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

9

Strana od-do

9

Název nakladatele

CEUR-WS

Místo vydání

Aachen

Místo konání akce

Lugano, Switzerland

Datum konání akce

9. 9. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—