Component Awareness in Convolutional Neural Networks
Component Awareness in Convolutional Neural Networks
复制标题
DOI：
10.1109/icdar.2017.72
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Brian Kenji Iwana;Letao Zhou;Kumiko Tanaka-Ishii;S. Uchida
中科院分区：
文献类型：
--
作者：
Brian Kenji Iwana;Letao Zhou;Kumiko Tanaka-Ishii;S. Uchida
在这项工作中，我们研究了卷积神经网络（CNN）推断构成图像的组件存在的能力。近年来，cnn在分类、检测、分割等方面取得了强大的成果。然而，这些模型从被检测对象的实例级监督中学习。在本文中，我们确定cnn是否可以在不定位的情况下使用图像级弱监督标签检测对象。为了证明CNN可以推断物体的感知，我们用一个只有字符级标记成分的汉字数据库来评估CNN的分类能力。我们表明，CNN能够在没有特定组件知识的情况下，在识别这些组件的存在方面达到很高的准确性。此外，我们通过将结果与去除组件的实验进行比较，验证了CNN正在推断目标组件的知识。这一研究对于诸如汉字识别等数据量大且没有鲁棒标注的应用具有重要意义。
In this work, we investigate the ability of Convolutional Neural Networks (CNN) to infer the presence of components that comprise an image. In recent years, CNNs have achieved powerful results in classification, detection, and segmentation. However, these models learn from instance-level supervision of the detected object. In this paper, we determine if CNNs can detect objects using image-level weakly supervised labels without localization. To demonstrate that a CNN can infer awareness of objects, we evaluate a CNN's classification ability with a database constructed of Chinese characters with only character-level labeled components. We show that the CNN is able to achieve a high accuracy in identifying the presence of these components without specific knowledge of the component. Furthermore, we verify that the CNN is deducing the knowledge of the target component by comparing the results to an experiment with the component removed. This research is important for applications with large amounts of data without robust annotation such as Chinese character recognition.