Capsule projection network (CapProNet) has shown its ability to obtain semantic information, and spatial structural information from the raw images. However, the vector capsule of CapProNet has limitations in representing semantic information due to ignoring local information. Besides, the number of trainable parameters also increases greatly with the dimension of the feature vector. To that end, we propose a matrix capsule convolution projection (MCCP) module by replacing the feature vector with a feature matrix, of which each column represents a local feature. The feature matrix is then convoluted by columns into capsule subspaces to decrease the number of trainable parameters effectively. Furthermore, the CapDetNet is designed to explore the structural information encoding of the MCCP module based on object detection task. Experimental results demonstrate that the proposed MCCP outperforms the baselines in image classification, and CapDetNet achieves the 2.3% performance gain in object detection.

中文翻译：

---

用于深度特征学习的矩阵胶囊卷积投影


胶囊投影网络（CapProNet）已显示出其从原始图像中获取语义信息和空间结构信息的能力。然而，CapProNet 的向量胶囊由于忽略了局部信息，在表示语义信息方面存在局限性。此外，可训练参数的数量也随着特征向量维数的增加而大大增加。为此，我们提出了一种矩阵胶囊卷积投影（MCCP）模块，通过用特征矩阵替换特征向量，其中每一列代表一个局部特征。然后将特征矩阵按列卷积成胶囊子空间，以有效减少可训练参数的数量。此外，CapDetNet旨在探索基于目标检测任务的MCCP模块的结构信息编码。实验结果表明，所提出的 MCCP 在图像分类方面优于基线，并且 CapDetNet 在目标检测方面实现了 2.3% 的性能增益。