arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02745cs.CVcs.LG
收藏

InverseForm:一种用于结构化边界感知分割的损失函数

InverseForm: A Loss Function for Structured Boundary-Aware Segmentation

Qualcomm AI Research(高通人工智能研究院)

Shubhankar Borse, Ying Wang, Yizhe Zhang, Fatih Porikli

摘要:

我们提出了一种新的边界感知损失项语义分割使用逆变换网络,有效地学习估计和目标边界之间的参数转换的程度。该插件损失项补充了捕获边界变换中的交叉熵损失,并允许在不增加其大小和计算复杂性的情况下对分割骨干模型进行一致且显著的性能改进。我们分析了我们的损失函数对三个室内和室外分割基准的定量和定性影响,包括Cityscapes,NYU-Depth-v2和PASCAL,将其集成到几个骨干网络的单任务和多任务设置的训练阶段。我们广泛的实验表明,所提出的方法始终优于基线,甚至在两个数据集上设置了新的最先进的方法。

英文摘要:

We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network, which efficiently learns the degree of parametric transformations between estimated and target boundaries. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations and allows consistent and significant performance improvement on segmentation backbone models without increasing their size and computational complexity. We analyze the quantitative and qualitative effects of our loss function on three indoor and outdoor segmentation benchmarks, including Cityscapes, NYU-Depth-v2, and PASCAL, integrating it into the training phase of several backbone networks in both single-task and multi-task settings. Our extensive experiments show that the proposed method consistently outperforms baselines, and even sets the new state-of-the-art on two datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑