arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1904.07934cs.CVcs.AI
收藏

魔鬼在边缘:从嘈杂的注释中学习语义边界

Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations

NVIDIA(英伟达);University of Toronto(多伦多大学);Vector Institute(向量研究所)

David Acuna, Amlan Kar, Sanja Fidler

摘要:

我们解决了语义边界预测的问题,其目的是识别属于对象(类)边界的像素。我们注意到,相关数据集包含大量的标签噪声,这反映了一个事实,即精确的注释很难获得,因此注释者需要权衡质量和效率。我们的目标是通过在训练过程中明确地推理注释噪声来学习清晰而精确的语义边界。我们提出了一个简单的新层和损失,可用于现有的基于学习的边界检测器。我们的层/损失强制检测器预测边缘处沿法线方向的最大响应,同时还正则化其方向。我们在训练过程中使用水平集公式进一步推理真实对象边界,这允许网络以端到端的方式从未对齐的标签中学习。实验表明,我们提高了超过4%的MF(ODS)和18.61%的AP方面的CASENet骨干网络,优于所有当前最先进的方法,包括那些处理对齐。此外,我们还证明了我们的学习网络可以用于显着改进粗略的分割标签,使其成为标记新数据的有效方法。

英文摘要:

We tackle the problem of semantic boundary prediction, which aims to identify pixels that belong to object(class) boundaries. We notice that relevant datasets consist of a significant level of label noise, reflecting the fact that precise annotations are laborious to get and thus annotators trade-off quality with efficiency. We aim to learn sharp and precise semantic boundaries by explicitly reasoning about annotation noise during training. We propose a simple new layer and loss that can be used with existing learning-based boundary detectors. Our layer/loss enforces the detector to predict a maximum response along the normal direction at an edge, while also regularizing its direction. We further reason about true object boundaries during training using a level set formulation, which allows the network to learn from misaligned labels in an end-to-end fashion. Experiments show that we improve over the CASENet backbone network by more than 4% in terms of MF(ODS) and 18.61% in terms of AP, outperforming all current state-of-the-art methods including those that deal with alignment. Furthermore, we show that our learned network can be used to significantly improve coarse segmentation labels, lending itself as an efficient way to label new data.

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。

↑