Poly-YOLO
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F20%3AA210268M" target="_blank" >RIV/61988987:17610/20:A210268M - isvavai.cz</a>
Result on the web
<a href="https://gitlab.com/irafm-ai/poly-yolo" target="_blank" >https://gitlab.com/irafm-ai/poly-yolo</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Poly-YOLO
Original language description
We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two of its weaknesses: a large amount of rewritten labels and inefficient distribution of anchors. Poly-YOLO reduces the issues by aggregating features from a light SE-Darknet-53 backbone with a hypercolumn technique, using stairstep upsampling, and produces a single scale output with high resolution. In comparison with YOLOv3, Poly-YOLO has only 60% of its trainable parameters but improves mAP by a relative 40%. We also present Poly-YOLO lite with fewer parameters and a lower output resolution. It has the same precision as YOLOv3, but it is three times smaller and twice as fast, thus suitable for embedded devices. Finally, Poly-YOLO performs instance segmentation using bounding polygons. The network is trained to detect size-independent polygons defined on a polar grid. Vertices of each polygon are being predicted with their confidence, and therefore Poly-YOLO produces polygons with a varying number of vertices. Source code is available at https://gitlab.com/irafm-ai/poly-yolo.
Czech name
—
Czech description
—
Classification
Type
R - Software
CEP classification
—
OECD FORD branch
10102 - Applied mathematics
Result continuities
Project
<a href="/en/project/EF17_049%2F0008414" target="_blank" >EF17_049/0008414: Centre for the development of Artificial Intelligence Methods for the Automotive Industry of the region</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Internal product ID
Poly-YOLO
Technical parameters
Inovativní model neuronové sítě vytvořený na základě YOLOv3. Neuronová síť je naučená detekovat objekty v obrazových datech pomocí ohraničení polygony. Model si zachovává rychlost YOLOv3 a řeší některé z jeho principiálních problémů. Celý projekt je realizován v jazyce Python za pomocí frameworků Tensorflow a Keras.
Economical parameters
Freeware, software si po jeho zveřejnění na veřejném repositáři, zkopírovaly desítky uživatelů.
Owner IČO
61988987
Owner name
Ostravská univerzita