Ghost-dil-NetVLAD：一种用于视觉地点识别的轻量级神经网络
Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition
AI总结：
针对视觉地点识别中计算成本与性能不平衡的问题，提出结合Ghost模块、空洞卷积和可学习VLAD层的轻量级端到端网络，在精度相近下大幅降低FLOPs与参数量。
摘要：
视觉地点识别（VPR）是一项具有挑战性的任务，面临巨大计算成本与高识别性能之间的不平衡。得益于轻量级卷积神经网络（CNN）实用的特征提取能力以及局部聚合描述符向量（VLAD）层的可训练性，我们提出了一种轻量级、弱监督的端到端神经网络，该网络由名为GhostCNN的前端感知模型和作为后端的可学习VLAD层组成。GhostCNN基于Ghost模块，这些模块是基于CNN的轻量级架构。它们能够使用线性运算而非传统卷积过程生成冗余特征图，从而在计算资源与识别精度之间实现良好的权衡。为进一步增强我们提出的轻量级模型，我们在Ghost模块中加入空洞卷积，以获取包含更多空间语义信息的特征，从而提高精度。最后，在一个常用公共基准和我们的私有数据集上进行的大量实验验证了所提出的神经网络将VGG16-NetVLAD的FLOPs和参数分别降低了99.04%和80.16%。此外，两个模型取得了相近的精度。
英文摘要：
Visual place recognition (VPR) is a challenging task with the unbalance between enormous computational cost and high recognition performance. Thanks to the practical feature extraction ability of the lightweight convolution neural networks (CNNs) and the train-ability of the vector of locally aggregated descriptors (VLAD) layer, we propose a lightweight weakly supervised end-to-end neural network consisting of a front-ended perception model called GhostCNN and a learnable VLAD layer as a back-end. GhostCNN is based on Ghost modules that are lightweight CNN-based architectures. They can generate redundant feature maps using linear operations instead of the traditional convolution process, making a good trade-off between computation resources and recognition accuracy. To enhance our proposed lightweight model further, we add dilated convolutions to the Ghost module to get features containing more spatial semantic information, improving accuracy. Finally, rich experiments conducted on a commonly used public benchmark and our private dataset validate that the proposed neural network reduces the FLOPs and parameters of VGG16-NetVLAD by 99.04% and 80.16%, respectively. Besides, both models achieve similar accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
