YOLO-ASC: You Only Look Once And See Contours

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F20%3AA21021UC" target="_blank" >RIV/61988987:17610/20:A21021UC - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9207223" target="_blank" >https://ieeexplore.ieee.org/document/9207223</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IJCNN48605.2020.9207223" target="_blank" >10.1109/IJCNN48605.2020.9207223</a>

Jazyk výsledku

angličtina

Název v původním jazyce

YOLO-ASC: You Only Look Once And See Contours

Popis výsledku v původním jazyce

YOLO is a useful, one-stage tool for object detection and classification. In this paper, we consider the application of grocery product detection. The grocery stores have a significant amount of product classes, so it is beneficial to postpone the classification into a second, specialized neural network with a higher capacity. Extracting bounding boxes for a classification network is not precise enough as the detected area includes redundant information about the background. We propose YOLO-ASC, which, for rectangular-based objects, detects bounding boxes together with object contour using a quadrangular. This approach allows detecting objects more accurately and without the background. For the quadrangular detection functionality, YOLO-ASC shares the feature maps that are already present in the network, and therefore its inference time is almost identical to the original YOLO. YOLO reaches high detection precision by using YOLO apriori knowledge, anchors extracted from data. In this work, we present two experiments where we demonstrate that YOLO-ASC training converges faster due to the symbiosis between the bounding box detection and quadrangular detection. Finally, we propose a tool for generating synthetic datasets with quadrangular labels that is helpful for transfer learning.

Název v anglickém jazyce

YOLO-ASC: You Only Look Once And See Contours

Popis výsledku anglicky

YOLO is a useful, one-stage tool for object detection and classification. In this paper, we consider the application of grocery product detection. The grocery stores have a significant amount of product classes, so it is beneficial to postpone the classification into a second, specialized neural network with a higher capacity. Extracting bounding boxes for a classification network is not precise enough as the detected area includes redundant information about the background. We propose YOLO-ASC, which, for rectangular-based objects, detects bounding boxes together with object contour using a quadrangular. This approach allows detecting objects more accurately and without the background. For the quadrangular detection functionality, YOLO-ASC shares the feature maps that are already present in the network, and therefore its inference time is almost identical to the original YOLO. YOLO reaches high detection precision by using YOLO apriori knowledge, anchors extracted from data. In this work, we present two experiments where we demonstrate that YOLO-ASC training converges faster due to the symbiosis between the bounding box detection and quadrangular detection. Finally, we propose a tool for generating synthetic datasets with quadrangular labels that is helpful for transfer learning.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

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)

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

2020 International Joint Conference on Neural Networks (IJCNN)

ISBN

978-1-7281-6926-2

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

1-7

Název nakladatele

IEEE

Místo vydání

USA

Místo konání akce

Glasgow , United Kingdom

Datum konání akce

19. 7. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—