Image Classifier with Dynamic Set of Known Classes

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F22%3AA2302GEE" target="_blank" >RIV/61988987:17610/22:A2302GEE - isvavai.cz</a>
Result on the web
<a href="https://ceur-ws.org/Vol-3226/paper8.pdf" target="_blank" >https://ceur-ws.org/Vol-3226/paper8.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Image Classifier with Dynamic Set of Known Classes
Original language description
The typical classification task is based on the assumption that the model will later only encounter examples of classes available during its training. In practice, this is often not a realistic assumption, because of limitations in obtaining enough labeled training data. This contribution is focused on the case where the model might encounter a sample belonging to a class different from the classes seen in the training phase. The goal is to reject examples of unseen classes with the option of later adding them as representatives of new classes without the need to retrain the backbone model. This is important because the end-user might not be able to re-train the model for any reason. The presented approach is based on metric learning combined with the meta-classifier similar to the approach of Xu et al. [1]. Classified examples are first embedded in a vector space through an encoder trained to capture similarities in the input data. The classification itself is then performed by ????, where ???? is the number of known classes, binary decisions. For each decision, the tested example is compared to the ???? closest examples from the given class. If the model does not decide that the example belongs to any class, this example is rejected as possibly unknown. The method is tested in a visual data classification task.
Czech name
—
Czech description
—

Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 22nd Conference Information Technologies - Applications and Theory (ITAT 2022)
ISBN
—
ISSN
1613-0073
e-ISSN
—
Number of pages
7
Pages from-to
68-74
Publisher name
CEUR-WS
Place of publication
—
Event location
Zuberec, Slovakia
Event date
Sep 23, 2022
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)