Towards Visual Classification Under Class Ambiguity
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00367286" target="_blank" >RIV/68407700:21230/23:00367286 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21730/23:00367286
Result on the web
<a href="https://doi.org/10.1109/ICRA48891.2023.10161568" target="_blank" >https://doi.org/10.1109/ICRA48891.2023.10161568</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICRA48891.2023.10161568" target="_blank" >10.1109/ICRA48891.2023.10161568</a>
Alternative languages
Result language
angličtina
Original language name
Towards Visual Classification Under Class Ambiguity
Original language description
Visual classification under uncertainty is a complex computer vision problem. We present a thorough comparison of several variants of convolutional neural network (CNN) classification techniques in the context of ambiguous image data interpretation. We explore possible improvements in classification accuracy achieved by insertion of prior ambiguity information during the annotation process. This enables us to harness known similarities between individual classes and use them as probability distributions for soft ground-truth labels. We also present an approach based on Bayesian CNNs, offering the possibility of further interpretation of classification results in a problem where the neural network model is often considered as a black box. The presented techniques are verified on a practical spot weld inspection problem.
Czech name
—
Czech description
—
Classification
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)
Result continuities
Project
<a href="/en/project/FW03010600" target="_blank" >FW03010600: Autonomous robotic system for ultrasonic and eddy current inspection of metal and composite parts of complex shapes</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2023 IEEE International Conference on Robotics and Automation
ISBN
979-8-3503-2365-8
ISSN
1050-4729
e-ISSN
2577-087X
Number of pages
7
Pages from-to
7032-7038
Publisher name
IEEE
Place of publication
Piscataway
Event location
Londýn
Event date
May 29, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001048371100005