BBRefinement: an universal scheme to improve precision of box object detectors
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F22%3AA23026BN" target="_blank" >RIV/61988987:17610/22:A23026BN - isvavai.cz</a>
Výsledek na webu
<a href="https://www.mdpi.com/2076-3417/12/7/3402/htm" target="_blank" >https://www.mdpi.com/2076-3417/12/7/3402/htm</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.3390/app12073402" target="_blank" >10.3390/app12073402</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
BBRefinement: an universal scheme to improve precision of box object detectors
Popis výsledku v původním jazyce
We present a conceptually simple yet powerful and general scheme for refining the predictions of bounding boxes produced by an arbitrary object detector. Our approach was trained separately on single objects extracted from ground truth labels. For inference, it can be coupled with an arbitrary object detector to improve its precision. The method, called BBRefinement, uses a mixture of data consisting of the image crop of an object and the object’s class and center. Because BBRefinement works in a restricted domain, it does not have to be concerned with multiscale detection, recognition of the object’s class, computing confidence, or multiple detections. Thus, the training is much more effective. It results in the ability to improve the performance of SOTA architectures by up to two mAP points on the COCO dataset in the benchmark. The refinement process is fast; it adds 50–80 ms overhead to a standard detector using RTX2080; therefore, it can run in real time on standard hardware. Finally, we show that BBRefinement can also be applied to COCO’s ground truth labels to create new, more precise labels. The link to the source code is provided in the contribution.
Název v anglickém jazyce
BBRefinement: an universal scheme to improve precision of box object detectors
Popis výsledku anglicky
We present a conceptually simple yet powerful and general scheme for refining the predictions of bounding boxes produced by an arbitrary object detector. Our approach was trained separately on single objects extracted from ground truth labels. For inference, it can be coupled with an arbitrary object detector to improve its precision. The method, called BBRefinement, uses a mixture of data consisting of the image crop of an object and the object’s class and center. Because BBRefinement works in a restricted domain, it does not have to be concerned with multiscale detection, recognition of the object’s class, computing confidence, or multiple detections. Thus, the training is much more effective. It results in the ability to improve the performance of SOTA architectures by up to two mAP points on the COCO dataset in the benchmark. The refinement process is fast; it adds 50–80 ms overhead to a standard detector using RTX2080; therefore, it can run in real time on standard hardware. Finally, we show that BBRefinement can also be applied to COCO’s ground truth labels to create new, more precise labels. The link to the source code is provided in the contribution.
Klasifikace
Druh
J<sub>imp</sub> - Článek v periodiku v databázi Web of Science
CEP obor
—
OECD FORD obor
10102 - Applied mathematics
Návaznosti výsledku
Projekt
<a href="/cs/project/EF17_049%2F0008414" target="_blank" >EF17_049/0008414: Centrum pro výzkum a vývoj metod umělé intelligence v automobilovém průmyslu regionu</a><br>
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2022
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
Applied Sciences
ISSN
2076-3417
e-ISSN
2076-3417
Svazek periodika
—
Číslo periodika v rámci svazku
7
Stát vydavatele periodika
CH - Švýcarská konfederace
Počet stran výsledku
12
Strana od-do
1-12
Kód UT WoS článku
000781328100001
EID výsledku v databázi Scopus
2-s2.0-85127765151