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

TL;DR

Poly-YOLO enhances YOLOv3 by increasing detection accuracy and adding instance segmentation, while reducing model size and improving speed, making it suitable for embedded devices.

Contribution

The paper introduces Poly-YOLO, a novel version of YOLOv3 that improves performance, reduces parameters, and incorporates instance segmentation with polygon detection.

Findings

Poly-YOLO achieves 40% higher mAP than YOLOv3.

Poly-YOLO lite is three times smaller and twice as fast as YOLOv3.

Poly-YOLO successfully performs size-independent polygon instance segmentation.

Abstract

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.