Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
复制标题
DOI：
--
复制
发表时间：
2015-02
期刊：
影响因子：
--
通讯作者：
G. Papandreou;Liang-Chieh Chen;K. Murphy;A. Yuille
中科院分区：
文献类型：
--
作者：
G. Papandreou;Liang-Chieh Chen;K. Murphy;A. Yuille
深度卷积神经网络(DCNN)对大量具有较强像素级标注的图像进行训练，极大地推动了语义图像分割的发展。我们研究了从(1)弱标注的训练数据(如包围盒或图像级标签)或(2)来自一个或多个数据集的少数强标记图像和多个弱标记图像的组合中学习DCNN以进行语义图像分割的更具挑战性的问题。在这些弱监督和半监督环境下，我们发展了期望最大化(EM)方法来训练语义图像分割模型。广泛的实验评估表明，所提出的技术可以学习在具有挑战性的Pascal VOC 2012图像分割基准上提供具有竞争力的结果的模型，而所需的标注工作量显著减少。我们在以下的HTTPS URL上分享了实现建议的系统的源代码
Deep convolutional neural networks (DCNNs) trained on a large number of images with strong pixel-level annotations have recently significantly pushed the state-of-art in semantic image segmentation. We study the more challenging problem of learning DCNNs for semantic image segmentation from either (1) weakly annotated training data such as bounding boxes or image-level labels or (2) a combination of few strongly labeled and many weakly labeled images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for semantic image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at this https URL