Boosting the Performance of Object Detection CNNs with Context-Based Anomaly Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00351755" target="_blank" >RIV/68407700:21230/21:00351755 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-67537-0_11" target="_blank" >https://doi.org/10.1007/978-3-030-67537-0_11</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-67537-0_11" target="_blank" >10.1007/978-3-030-67537-0_11</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Boosting the Performance of Object Detection CNNs with Context-Based Anomaly Detection

Popis výsledku v původním jazyce

In this paper, we employ anomaly detection methods to enhance the ability of object detectors by using the context of their detections. This has numerous potential applications from boosting the performance of standard object detectors, to the preliminary validation of annotation quality, and even for robotic exploration and object search. We build our method on autoencoder networks for detecting anomalies, where we do not try to filter incoming data based on anomality score as is usual, but instead, we focus on the individual features of the data representing an actual scene. We show that one can teach autoencoders about the contextual relationship of objects in images, i.e. the likelihood of co-detecting classes in the same scene. This can then be used to identify detections that do and do not fit with the rest of the current observations in the scene. We show that the use of this information yields better results than using traditional thresholding when deciding if weaker detections are actually classed as observed or not. The experiments performed not only show that our method significantly improves the performance of CNN object detectors, but that it can be used as an efficient tool to discover incorrectly-annotated images

Název v anglickém jazyce

Boosting the Performance of Object Detection CNNs with Context-Based Anomaly Detection

Popis výsledku anglicky

In this paper, we employ anomaly detection methods to enhance the ability of object detectors by using the context of their detections. This has numerous potential applications from boosting the performance of standard object detectors, to the preliminary validation of annotation quality, and even for robotic exploration and object search. We build our method on autoencoder networks for detecting anomalies, where we do not try to filter incoming data based on anomality score as is usual, but instead, we focus on the individual features of the data representing an actual scene. We show that one can teach autoencoders about the contextual relationship of objects in images, i.e. the likelihood of co-detecting classes in the same scene. This can then be used to identify detections that do and do not fit with the rest of the current observations in the scene. We show that the use of this information yields better results than using traditional thresholding when deciding if weaker detections are actually classed as observed or not. The experiments performed not only show that our method significantly improves the performance of CNN object detectors, but that it can be used as an efficient tool to discover incorrectly-annotated images

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering

ISBN

978-3-030-67536-3

ISSN

1867-8211

e-ISSN

—

Počet stran výsledku

18

Strana od-do

159-176

Název nakladatele

Springer Nature

Místo vydání

—

Místo konání akce

Shanghai

Datum konání akce

16. 10. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—