Number of the records: 1
Coral Reef annotation, localisation and pixel-wise classification using Mask R-CNN and Bag of Tricks
- 1.
SYSNO ASEP 0536765 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Coral Reef annotation, localisation and pixel-wise classification using Mask R-CNN and Bag of Tricks Author(s) Picek, L. (CZ)
Říha, A. (CZ)
Zita, Aleš (UTIA-B) RID, ORCIDNumber of authors 3 Article number 83 Source Title CEUR Workshop Proceedings : Volume 2696. Working Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum. - Achen : CEUR-WS.org, 2020 - ISSN 1613-0073 Number of pages 12 s. Publication form Online - E Action CLEF 2020 Event date 22.09.2020 - 25.09.2020 VEvent location Thessaloniki Country GR - Greece Event type WRD Language eng - English Country DE - Germany Keywords Deep Learning ; Computer Vision ; Instance Segmentation Subject RIV JD - Computer Applications, Robotics OECD category Robotics and automatic control Institutional support UTIA-B - RVO:67985556 Annotation This article describes an automatic system for detection, classification and segmentation of individual coral substrates in underwater images. The proposed system achieved the best performances in both tasks of the second edition of the ImageCLEFcoral competition. Specifically, mean average precision with Intersection over Union (IoU) greater then 0.5 (mAP@0.5) of 0.582 in case of Coral reef image annotation and localisation, and mAP@0.5 of 0.678 in Coral reef image pixel-wise parsing. The system is based on Mask R-CNN object detection and instance segmentation framework boosted by advanced training strategies, pseudo-labeling, test-time augmentations, and Accumulated Gradient Normalisation. To support future research, code has been made available at: https://github.com/picekl/ImageCLEF2020-DrawnUI. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2021
Number of the records: 1