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 2005.13053cs.CVcs.LGeess.IV
收藏

使用递归近似任务进行图像分割的多任务深度学习

Multi-task deep learning for image segmentation using recursive approximation tasks

University of Cambridge(剑桥大学);University of Bordeaux(波尔多大学);CNRS(法国国家科学研究中心);Unilever R&D Colworth(联合利华研发中心科尔沃思)

Rihuan Ke, Aurélie Bugeau, Nicolas Papadakis, Mark Kirkland, Peter Schuetz, Carola-Bibiane Schönlieb

摘要:

用于分割的全监督深度神经网络通常需要大量的像素级标签,手动创建这些标签的成本很高。在这项工作中,我们开发了一种多任务学习方法来放松这一约束。我们把分割问题作为一个序列的近似子问题,递归定义,并在不断增加的近似精度。这些子问题由一个框架处理,该框架包括:1)从一小部分图像的像素级真实分割掩模学习的分割任务,2)从每个对象实例的部分掩模开始进行部分对象区域学习和数据驱动掩模进化的递归近似任务,以及3)其它面向问题的辅助任务,其用稀疏注释训练并促进专用特征的学习。大多数训练图像仅由不包含精确对象边界的(粗糙)部分掩码标记,而不是由其完整的分割掩码标记。在训练阶段,近似任务学习这些部分掩模的统计数据,并且部分区域以完全数据驱动的方式在来自分割任务的学习信息的帮助下朝向对象边界递归地增加。该网络是在极少量的精确分割图像和大量粗糙标签上训练的。因此,可以以便宜的方式获得注释。我们证明了我们的方法在三个应用程序中的效率与显微镜图像和超声图像。

英文摘要:

Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard the segmentation problem as a sequence of approximation subproblems that are recursively defined and in increasing levels of approximation accuracy. The subproblems are handled by a framework that consists of 1) a segmentation task that learns from pixel-level ground truth segmentation masks of a small fraction of the images, 2) a recursive approximation task that conducts partial object regions learning and data-driven mask evolution starting from partial masks of each object instance, and 3) other problem oriented auxiliary tasks that are trained with sparse annotations and promote the learning of dedicated features. Most training images are only labeled by (rough) partial masks, which do not contain exact object boundaries, rather than by their full segmentation masks. During the training phase, the approximation task learns the statistics of these partial masks, and the partial regions are recursively increased towards object boundaries aided by the learned information from the segmentation task in a fully data-driven fashion. The network is trained on an extremely small amount of precisely segmented images and a large set of coarse labels. Annotations can thus be obtained in a cheap way. We demonstrate the efficiency of our approach in three applications with microscopy images and ultrasound images.

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。

↑