论文标题
地理-SIC：在深图像分类器中学习可变形的几何形状
Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers
论文作者
论文摘要
可变形的形状提供了图像中显示的对象的重要而复杂的几何特征。但是，在许多图像分析任务中，这些信息通常被视为隐含知识的缺失或不足。本文介绍了Geo-SIC，这是第一个在变形空间中学习可变形形状的深度学习模型，以改善图像分类的性能。我们引入了一个新设计的框架，（i）同时从图像和潜在形状空间中衍生出具有较大级别内变体的特征； （ii）通过允许直接访问图像数据的基本几何特征来提高模型的解释性。特别是，我们开发了一个增强的分类网络，该网络配备了对几何形状表示的无监督学习，其特征是每个类别内的差异变换。与使用预提取形状的先前方法相反，我们的模型通过自然地学习与图像分类器共同学习最相关的形状特征，从而提供了一种更基本的方法。我们证明了我们方法对模拟2D图像和实际3D脑磁共振（MR）图像的有效性。实验结果表明，我们的模型基本上提高了图像分类精度，并具有增加模型可解释性的附加优势。我们的代码可在https://github.com/jw4hv/geo-sic上公开获取
Deformable shapes provide important and complex geometric features of objects presented in images. However, such information is oftentimes missing or underutilized as implicit knowledge in many image analysis tasks. This paper presents Geo-SIC, the first deep learning model to learn deformable shapes in a deformation space for an improved performance of image classification. We introduce a newly designed framework that (i) simultaneously derives features from both image and latent shape spaces with large intra-class variations; and (ii) gains increased model interpretability by allowing direct access to the underlying geometric features of image data. In particular, we develop a boosted classification network, equipped with an unsupervised learning of geometric shape representations characterized by diffeomorphic transformations within each class. In contrast to previous approaches using pre-extracted shapes, our model provides a more fundamental approach by naturally learning the most relevant shape features jointly with an image classifier. We demonstrate the effectiveness of our method on both simulated 2D images and real 3D brain magnetic resonance (MR) images. Experimental results show that our model substantially improves the image classification accuracy with an additional benefit of increased model interpretability. Our code is publicly available at https://github.com/jw4hv/Geo-SIC
