Image annotation with incomplete labelling by modelling image specific structured loss
Image annotation with incomplete labelling by modelling image specific structured loss
复制标题
DOI：
10.1002/tee.22190
复制
发表时间：
2015-10
影响因子：
1
通讯作者：
Xing Xu;Atsushi Shimada;H. Nagahara;R. Taniguchi;Li He
中科院分区：
文献类型：
--
作者：
Xing Xu;Atsushi Shimada;H. Nagahara;R. Taniguchi;Li He
在本文中，我们解决的问题，图像标注与不完整的标签，在每个训练图像中的多个对象没有完全标记。传统的一对全支持向量机（OVA-SVM）在完全标记上表现得相当好，但在不完全的情况下会急剧衰减。最近，提出了一种称为OVA-SSVM的结构化输出学习方法，通过对标签的结构化关联进行建模来提高OVA-SVM的性能，并在不完全设置下显示效率。OVA-SSVM假设每个训练样本包括单个标签，并采用分类风格的损失度量，只要其中一个预测标签是正确的，则整体预测应被视为正确。但是，这可能不适合多标签注释任务。因此，我们将OVA-SSVM方法扩展到多标签情况，并设计了一种新的图像特定的结构化损失来解释依赖于图像标签关联的预测标签之间的依赖性。所提出的特定于图像的结构化损失的优势在于，它可以直接从训练数据中学习标签的语义关系，而无需预定义的语义层次。在各种基准数据集上的大量实证结果表明，所提出的方法在不完整标记的图像注释任务上的性能明显优于OVA-SSVM，并且与其他最先进的方法相比，具有竞争力的性能。© 2015日本电气工程师协会。出版社：John Wiley & Sons，Inc.
In this paper, we address the problem of image annotation with incomplete labeling, where multiple objects in each training image are not fully labeled. The conventional one‐versus‐all support vector machine (OVA‐SVM), which performs fairly well on full labeling, decays drastically under the setting of incompleteness. Recently, a structured output learning method termed OVA‐SSVM was proposed to boost the performance of OVA‐SVM by modeling the structured associations of labels and show efficiency under the setting of incompleteness. OVA‐SSVM assumes that each training sample includes a single label and adopts an loss measure of classification style where, as long as one of the predicted label is correct, the overall prediction should be considered correct. However, this may not be appropriate for the multilabel annotation task. Therefore, we extend the OVA‐SSVM method to the multilabel situation and design a novel image‐specific structured loss to account for the dependences between predicted labels relying on image label associations. The superiority of the proposed image‐specific structured loss is that it can directly learn the semantic relationships of labels from training data without predefined semantic hierarchy. Extensive empirical results on a variety of benchmark datasets show that the proposed method performs significantly better than OVA‐SSVM on image annotation tasks with incomplete labeling and achieves competitive performance compared to other state‐of‐the‐art methods. © 2015 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.