Szczegóły publikacji
Opis bibliograficzny
YOLOv3 precision improvement by the weighted centers of confidence selection / Adrian HORZYK, Efe Ergün // W: IJCNN 2020 [Dokument elektroniczny] : 2020 International Joint Conference on Neural Networks : [July 19–24, 2020, virtually]. — Wersja do Windows. — Dane tekstowe. — Piscataway : IEEE, cop. 2020. — (Proceedings of ... International Joint Conference on Neural Networks ; ISSN 2161-4393). — Dod. ISBN Print on Demand(PoD): 978-1-7281-6927-9. — e-ISBN: 978-1-7281-6926-2. — S. [1–8]. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. [8], Abstr. — Publikacja dostępna online od: 2020-09-28
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 130528 |
|---|---|
| Data dodania do BaDAP | 2020-10-05 |
| Tekst źródłowy | URL |
| DOI | 10.1109/IJCNN48605.2020.9206848 |
| Rok publikacji | 2020 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | IEEE International Joint Conference on Neural Networks 2020 |
| Czasopismo/seria | Proceedings of ... International Joint Conference on Neural Networks |
Abstract
One of the most popular and widely used object detection algorithm today is the YOLOv3 due to its high performance and speed. However, YOLOv3 is not the best algorithm in terms of precision. This paper introduces a substantial change to the post-processing routine of the YOLOv3 after the prediction to increase its final accuracy. Currently, YOLOv3 uses a Non-Max Suppression algorithm to eliminate multiple detections of the same object. This algorithm is picking the most confident overlaying box on any object to present it as the final prediction. This paper presents a new algorithm called Weighted Centers of Confidence Selection that increases the precision using a confidence-weighted average bounding box as a replacement to the existing bounding boxes without making any changes to the YOLOv3 convolutional neural network. We demonstrate how this algorithm works and compare its results to the results achieved by the YOLO’s Non-Max Suppression algorithm, focusing on precision and achieving almost the same frame-speed as the original YOLOv3. This new approach allowed us to improve the average accuracy on the COCO dataset in comparison to the original YOLO’s Non-Max Suppression.
