arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.06050cs.CVcs.LGeess.IV
收藏

基于类增量学习的语义分割方法

Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels

Technische Universität Braunschweig(布伦瑞克工业大学)

Marvin Klingner, Andreas Bär, Philipp Donn, Tim Fingscheidt

摘要:

虽然经过语义分割训练的神经网络对于自动驾驶中的感知至关重要,但大多数当前算法假设固定数量的类,这在开发需要额外类的新自动驾驶系统时存在重大限制。在本文中,我们提出了一种技术,实现类增量学习的语义分割,而不使用标记的数据,模型最初的trained.Previous方法仍然依赖于标签的旧类和新类,或无法正确区分它们。我们展示了如何克服这些问题与一种新的类增量学习技术,但需要标签只为新的类。具体来说,(i)我们引入了一个新的损失函数,既不依赖于旧数据,也不依赖于旧标签,(ii)我们展示了如何将新的类以模块化的方式集成到预先训练的语义分割模型中,最后(iii)我们在统一的设置中重新实现了以前的方法,以将它们与我们的方法进行比较。我们在Cityscapes数据集上评估了我们的方法,在那里我们超过了所有基线的mIoU性能3.5%的绝对值,达到了一个结果,这只比单阶段训练的性能上限低2.2%的绝对值,同时依赖于所有数据和标签。

英文摘要:

While neural networks trained for semantic segmentation are essential for perception in autonomous driving, most current algorithms assume a fixed number of classes, presenting a major limitation when developing new autonomous driving systems with the need of additional classes. In this paper we present a technique implementing class-incremental learning for semantic segmentation without using the labeled data the model was initially trained on. Previous approaches still either rely on labels for both old and new classes, or fail to properly distinguish between them. We show how to overcome these problems with a novel class-incremental learning technique, which nonetheless requires labels only for the new classes. Specifically, (i) we introduce a new loss function that neither relies on old data nor on old labels, (ii) we show how new classes can be integrated in a modular fashion into pretrained semantic segmentation models, and finally (iii) we re-implement previous approaches in a unified setting to compare them to ours. We evaluate our method on the Cityscapes dataset, where we exceed the mIoU performance of all baselines by 3.5% absolute reaching a result, which is only 2.2% absolute below the upper performance limit of single-stage training, relying on all data and labels simultaneously.

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。

↑