Deep convolutional neural networks have largely benefited computer vision tasks. However, the high computational complexity limits their real-world applications. To this end, many methods have been proposed for efficient network learning, and applications in portable mobile devices. In this paper, we propose a novel Moving-Mobile-Network, named M ² Net, for landmark recognition, equipped each landmark image with located geographic information. We intuitively find that M ² Net can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy. The above intuition is achieved by our proposed reward function with the input of geo-location and landmarks. We also find that the performance of other portable networks can be improved via our architecture. We construct two landmark image datasets, with each landmark associated with geographic information, over which we conduct extensive experiments to demonstrate that M ² Net achieves improved recognition accuracy with comparable complexity.

中文翻译：

---

多样化的推理路径选择：用于地标识别的移动网络

深度卷积神经网络在很大程度上有利于计算机视觉任务。但是，高计算复杂度限制了其实际应用。为此，已经提出了许多方法用于有效的网络学习以及在便携式移动设备中的应用。在本文中，我们提出了一种新颖的名为M ² Net的移动移动网络 ，用于地标识别，为每个地标图像配备了定位的地理信息。我们直观地发现M ² Net可以从根本上促进推理路径（所选块子集）选择的多样性，从而提高识别的准确性。上述直觉是通过我们提出的奖励功能以及地理位置和地标的输入来实现的。我们还发现，通过我们的体系结构可以提高其他便携式网络的性能。我们构建了两个地标图像数据集，每个地标都与地理信息相关联，在此数据集上我们进行了广泛的实验，以证明M ² Net以可比较的复杂度实现了更高的识别精度。