Constrained-CNN losses for weakly supervised segmentation
Constrained-CNN losses for weakly supervised segmentation
复制标题
DOI：
10.1016/j.media.2019.02.009
复制
发表时间：
2019-05-01
影响因子：
10.9
通讯作者：
Ben Ayed, Ismail
中科院分区：
文献类型：
--
作者：
Kervadec, Hoel;Dolz, Jose;Ben Ayed, Ismail
弱监督学习基于，例如，部分标记的图像或图像标签目前在CNN分割中引起了极大的关注，因为它可以减轻对完整和费力的像素/体素注释的需求。对网络输出强制执行高阶（全局）不等式约束（例如，约束目标区域的大小）可以利用未标记的数据，用特定领域的知识指导训练过程。不等式约束是非常灵活的，因为它们不假设精确的先验知识。然而，约束拉格朗日对偶优化在深度网络中基本上被避免，主要是出于计算易处理性的原因。据我们所知，Pathak et al.（2015 a）的方法是唯一一个在弱监督分割中解决具有线性约束的深度CNN的先前工作。它使用约束从弱标签合成完全标记的训练掩码（建议），模仿完全监督并促进双重优化。我们建议引入可微惩罚，直接在损失函数中强制不等式约束，避免昂贵的拉格朗日双重迭代和建议生成。从约束优化的角度来看，我们简单的基于惩罚的方法不是最优的，因为不能保证满足约束。然而，令人惊讶的是，它比Pathak等人（2015 a）中基于拉格朗日的约束CNN产生了更好的结果，同时减少了训练的计算需求。通过只标注一小部分像素，所提出的方法可以达到与三个单独任务的全面监督相当的分割性能水平。虽然我们的实验集中在基本的线性约束，如目标区域大小和图像标签，我们的框架可以很容易地扩展到其他非线性约束，例如，不变形状矩（Klodt和Cremers，2011）和其他区域统计（Lim等人，2014年）。因此，它有可能缩小语义医学图像分割中弱监督学习和全监督学习之间的差距。我们的代码是公开的。(C)2019 Elsevier B. V.版权所有。
Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. Enforcing high-order (global) inequality constraints on the network output (for instance, to constrain the size of the target region) can leverage unlabeled data, guiding the training process with domain-specific knowledge. Inequality constraints are very flexible because they do not assume exact prior knowledge. However, constrained Lagrangian dual optimization has been largely avoided in deep networks, mainly for computational tractability reasons. To the best of our knowledge, the method of Pathak et al. (2015a) is the only prior work that addresses deep CNNs with linear constraints in weakly supervised segmentation. It uses the constraints to synthesize fully-labeled training masks (proposals) from weak labels, mimicking full supervision and facilitating dual optimization.We propose to introduce a differentiable penalty, which enforces inequality constraints directly in the loss function, avoiding expensive Lagrangian dual iterates and proposal generation. From constrained-optimization perspective, our simple penalty-based approach is not optimal as there is no guarantee that the constraints are satisfied. However, surprisingly, it yields substantially better results than the Lagrangian-based constrained CNNs in Pathak et al. (2015a), while reducing the computational demand for training. By annotating only a small fraction of the pixels, the proposed approach can reach a level of segmentation performance that is comparable to full supervision on three separate tasks. While our experiments focused on basic linear constraints such as the target-region size and image tags, our framework can be easily extended to other non-linear constraints, e.g., invariant shape moments (Klodt and Cremers, 2011) and other region statistics (Lim et al., 2014). Therefore, it has the potential to close the gap between weakly and fully supervised learning in semantic medical image segmentation. Our code is publicly available. (C) 2019 Elsevier B.V. All rights reserved.