English

TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency

Computer Vision and Pattern Recognition 2023-09-19 v5

Abstract

This paper addresses the task of semantic segmentation in computer vision, aiming to achieve precise pixel-wise classification. We investigate the joint training of models for semantic edge detection and semantic segmentation, which has shown promise. However, implicit cross-task consistency learning in multi-task networks is limited. To address this, we propose a novel "decoupled cross-task consistency loss" that explicitly enhances cross-task consistency. Our semantic segmentation network, TriangleNet, achieves a substantial 2.88\% improvement over the Baseline in mean Intersection over Union (mIoU) on the Cityscapes test set. Notably, TriangleNet operates at 77.4\% mIoU/46.2 FPS on Cityscapes, showcasing real-time inference capabilities at full resolution. With multi-scale inference, performance is further enhanced to 77.8\%. Furthermore, TriangleNet consistently outperforms the Baseline on the FloodNet dataset, demonstrating its robust generalization capabilities. The proposed method underscores the significance of multi-task learning and explicit cross-task consistency enhancement for advancing semantic segmentation and highlights the potential of multitasking in real-time semantic segmentation.

Keywords

Cite

@article{arxiv.2210.05152,
  title  = {TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency},
  author = {Dan Zhang and Rui Zheng and Luosang Gadeng and Pei Yang},
  journal= {arXiv preprint arXiv:2210.05152},
  year   = {2023}
}

Comments

Accepted for publication in the journal "International Journal of Intelligent Systems"

R2 v1 2026-06-28T03:12:37.026Z