GHA-Inst: a real-time instance segmentation model utilizing YOLO detection framework

Chengang Dong

doi:10.1007/s10586-024-04373-y

GHA-Inst: a real-time instance segmentation model utilizing YOLO detection framework

2024-03-23

0

PRE

AI

DOI：10.1007/s10586-024-04373-y

Original

Original request for help

Save

Abstract

En 中文

The real-time instance segmentation task based on deep learning aims to accurately identify and distinguish all instance objects from images or videos. However, due to the existence of problems such as mutual occlusion between instances, limitations in model receptive fields, etc., achieving accurate and real-time segmentation continues to pose a formidable challenge. To alleviate the aforementioned issues, this paper proposes a real-time instance segmentation method based on a dual-branch structure, called GHA-Inst. Specifically, we made improvements to the feature fusion module (Neck) and output end (Head) of the YOLOv7-seg real-time instance segmentation framework to mitigate the accuracy reduction caused by feature loss and reduce the interference of background noise on the model. Secondly, we introduced a Global Hybrid-Domain Attention (GHA) module to improve the model's focus on significant information while retaining more original spatial features, alleviate incomplete segmentation caused by instance occlusion, and improve the quality of generated masks. Finally, our method achieved competitive results on multiple metrics of the MS COCO 2017 and KINS open-source datasets. Compared with the YOLOv7-seg baseline model, GHA-Inst improved the average precision (AP) by 3.4% and 2.6% on the two datasets, respectively.

Keywords:

Instance segmentation

Attention mechanisms

YOLOv7

GHA-Inst: a real-time instance segmentation model utilizing YOLO detection framework

Abstract

Journal

Organization