当前位置: X-MOL 学术Mach. Vis. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
ConsInstancy: learning instance representations for semi-supervised panoptic segmentation of concrete aggregate particles
Machine Vision and Applications ( IF 3.3 ) Pub Date : 2022-07-04 , DOI: 10.1007/s00138-022-01313-x
Max Coenen, Tobias Schack, Dries Beyer, Christian Heipke, Michael Haist

We present a semi-supervised method for panoptic segmentation based on ConsInstancy regularisation, a novel strategy for semi-supervised learning. It leverages completely unlabelled data by enforcing consistency between predicted instance representations and semantic segmentations during training in order to improve the segmentation performance. To this end, we also propose new types of instance representations that can be predicted by one simple forward path through a fully convolutional network (FCN), delivering a convenient and simple-to-train framework for panoptic segmentation. More specifically, we propose the prediction of a three-dimensional instance orientation map as intermediate representation and two complementary distance transform maps as final representation, providing unique instance representations for a panoptic segmentation. We test our method on two challenging data sets of both, hardened and fresh concrete, the latter being proposed by the authors in this paper demonstrating the effectiveness of our approach, outperforming the results achieved by state-of-the-art methods for semi-supervised segmentation. In particular, we are able to show that by leveraging completely unlabelled data in our semi-supervised approach the achieved overall accuracy (OA) is increased by up to 5% compared to an entirely supervised training using only labelled data. Furthermore, we exceed the OA achieved by state-of-the-art semi-supervised methods by up to 1.5%.



中文翻译:

ConsInstancy:学习实例表示,用于混凝土骨料颗粒的半监督全景分割

我们提出了一种基于 ConsInstancy 正则化的全景分割半监督方法,这是一种新的半监督学习策略。它通过在训练期间强制预测实例表示和语义分割之间的一致性来利用完全未标记的数据,以提高分割性能。为此,我们还提出了新类型的实例表示,这些表示可以通过一个简单的前向路径通过全卷积网络 (FCN) 进行预测,为全景分割提供了一个方便且易于训练的框架。更具体地说,我们建议将 3D 实例方向图的预测作为中间表示,将两个互补距离变换图作为最终表示,为全景分割提供独特的实例表示。我们在两个具有挑战性的数据集上测试我们的方法,硬化混凝土和新拌混凝土,后者是作者在本文中提出的,证明了我们方法的有效性,优于最先进的半混凝土方法取得的结果。监督分割。特别是,我们能够证明,通过在我们的半监督方法中利用完全未标记的数据,与仅使用标记数据的完全监督训练相比,实现的总体准确度 (OA) 提高了 5%。此外,我们比最先进的半监督方法实现的 OA 高出 1.5%。优于最先进的半监督分割方法所取得的结果。特别是,我们能够证明,通过在我们的半监督方法中利用完全未标记的数据,与仅使用标记数据的完全监督训练相比,实现的总体准确度 (OA) 提高了 5%。此外,我们比最先进的半监督方法实现的 OA 高出 1.5%。优于最先进的半监督分割方法所取得的结果。特别是,我们能够证明,通过在我们的半监督方法中利用完全未标记的数据,与仅使用标记数据的完全监督训练相比,实现的总体准确度 (OA) 提高了 5%。此外,我们比最先进的半监督方法实现的 OA 高出 1.5%。

更新日期:2022-07-05
down
wechat
bug