Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3

• Published in: Neural computing & applications 2022-05, Vol.34 (10), p.8275-8290
• Main Authors: Hurtik, Petr, Molek, Vojtech, Hula, Jan, Vajgl, Marek, Vlasanek, Pavel, Nejezchleba, Tomas
• Format: Article
• Language: English
• Subjects: Apexes; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Electronic devices; Image Processing and Computer Vision; Instance segmentation; Original Article; Parameters; Polygons; Probability and Statistics in Computer Science; Source code
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-021-05978-9

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 an 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 the mean average precision 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 by 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 .