论文标题
Trianglenet：Edge先验增强网络通过交叉任务一致性进行语义分割
TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
论文作者
论文摘要
本文解决了计算机视觉中语义细分的任务，旨在实现精确的像素分类。我们研究了用于语义边缘检测和语义分割的模型的联合培训，这表明了希望。但是，多任务网络中的隐式交叉任务一致性学习是有限的。为了解决这个问题，我们提出了一种新颖的“取消交叉任务一致性损失”，可以明确提高交叉任务的一致性。我们的语义分割网络Trianglenet在CityScapes测试集上的平均交叉点（MIOU）中的基线比基线方面取得了可观的2.88 \％。值得注意的是，Trianglenet在CityScapes上以77.4 \％miou/46.2 fps运行，以完全分辨率展示实时推理功能。通过多尺度推断，性能进一步提高到77.8 \％。此外，Trianglenet始终优于Floodnet数据集上的基线，证明其强大的概括能力。提出的方法强调了多任务学习和明确的交叉任务一致性提高对扩展语义细分的重要性，并突出了在实时语义分段中多任务处理的潜力。
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.
