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 1507.07583cs.CV
收藏

自动上下文决策森林到深度ConvNets的映射用于语义分割

Mapping Auto-context Decision Forests to Deep ConvNets for Semantic Segmentation

Heidelberg University(海德堡大学);Harvard Medical School(哈佛医学院);BIH/MDC(柏林卫生研究院/马克斯·德尔布吕克分子医学中心);University of Twente(特文特大学);MPI-CBG(马克斯·普朗克分子细胞生物学与遗传学研究所)

David L. Richmond, Dagmar Kainmueller, Michael Y. Yang, Eugene W. Myers, Carsten Rother

摘要:

我们考虑的任务,逐像素的语义分割给定一个小的一组标记的训练图像。解决这一任务的两种最流行的技术是决策森林(DF)和神经网络(NN)。在这项工作中,我们探讨了这些技术的两种特殊形式之间的关系:堆叠DF(即自动上下文)和深度卷积神经网络(ConvNet)。我们的主要贡献是证明自动上下文可以映射到具有新颖架构的深度ConvNet,从而进行端到端的训练。这种映射可以用作深度ConvNet的初始化,即使面对非常有限的训练数据也可以进行训练。我们还展示了从改进的ConvNet到第二个堆叠DF的近似映射,与原始的相比,性能有所提高。我们通过实验验证,这些映射优于堆叠的DF在计算机视觉和生物学中的两个不同的应用:基于Kinect的身体部位标记从深度图像,和体节分割显微镜图像的发展中的斑马鱼。最后,我们重新审视核心映射从决策树(DT)到NN,并表明,它也可以映射一个模糊DT,与sigmoidal分裂决策,NN。这解决了先前映射的多个限制,并对流行的整流线性单元(ReLU)以及最近提出的级联ReLU(CReLU)激活函数产生了新的见解。

英文摘要:

We consider the task of pixel-wise semantic segmentation given a small set of labeled training images. Among two of the most popular techniques to address this task are Decision Forests (DF) and Neural Networks (NN). In this work, we explore the relationship between two special forms of these techniques: stacked DFs (namely Auto-context) and deep Convolutional Neural Networks (ConvNet). Our main contribution is to show that Auto-context can be mapped to a deep ConvNet with novel architecture, and thereby trained end-to-end. This mapping can be used as an initialization of a deep ConvNet, enabling training even in the face of very limited amounts of training data. We also demonstrate an approximate mapping back from the refined ConvNet to a second stacked DF, with improved performance over the original. We experimentally verify that these mappings outperform stacked DFs for two different applications in computer vision and biology: Kinect-based body part labeling from depth images, and somite segmentation in microscopy images of developing zebrafish. Finally, we revisit the core mapping from a Decision Tree (DT) to a NN, and show that it is also possible to map a fuzzy DT, with sigmoidal split decisions, to a NN. This addresses multiple limitations of the previous mapping, and yields new insights into the popular Rectified Linear Unit (ReLU), and more recently proposed concatenated ReLU (CReLU), activation functions.

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。

↑