MSDA-SparseInst: Real-Time Instance Segmentation via Multi-Scale Feature Fusion and Dual-Branch Attention
Journal of Computing and Electronic Information Management · 26.03.2026 · 20 (3) · 79-87
DOI: 10.54097/e5s94861 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computing and Electronic Information Management, online erschienen am 26.03.2026. Verfasst von Yinghao Chen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Real-time instance segmentation is crucial for urban road-scene understanding, where accurate pixel-level perception is required under complex backgrounds, occlusion, and large scale variation. However, existing efficient methods often struggle to balance segmentation accuracy and inference speed, especially for small distant objects and densely distributed instances. To address this issue, this paper proposes MSDA-SparseInst, a real-time instance segmentation framework based on SparseInst. Specifically, an improved backbone is adopted to enhance feature extraction, a Multi-scale Dilated Feature Aggregation (MDFA) module is introduced to strengthen cross-scale contextual modeling, and a lightweight dual-branch attention strategy composed of GCSA and GGCA is designed to refine decoder features. Experimental results on the Cityscapes validation set show that the proposed method achieves 21.8 AP, 43.4 AP50, and 18.1 AP75 at 30.7 FPS, improving the baseline SparseInst by 3.0 AP while maintaining real-time performance. The results demonstrate that MSDA-SparseInst provides a better trade-off between segmentation accuracy and efficiency for urban road-scene instance segmentation.
Zitieren
APA
Chen, Y. (2026). MSDA-SparseInst: Real-Time Instance Segmentation via Multi-Scale Feature Fusion and Dual-Branch Attention. Journal of Computing and Electronic Information Management, 20(3), 79-87. https://doi.org/10.54097/e5s94861
Vancouver
Chen Y. MSDA-SparseInst: Real-Time Instance Segmentation via Multi-Scale Feature Fusion and Dual-Branch Attention. Journal of Computing and Electronic Information Management. 2026;20(3):79-87. doi:10.54097/e5s94861
BibTeX
@article{Chen2026,
author = {Chen, Yinghao},
title = {MSDA-SparseInst: Real-Time Instance Segmentation via Multi-Scale Feature Fusion and Dual-Branch Attention},
journal = {Journal of Computing and Electronic Information Management},
year = {2026},
volume = {20},
number = {3},
pages = {79--87},
doi = {10.54097/e5s94861}
}
EUVIMED