论文标题
实时本地功能，具有全局视觉信息增强
Real-time Local Feature with Global Visual Information Enhancement
论文作者
论文摘要
本地功能为各种视觉任务提供紧凑而不变的图像表示。当前基于深度学习的本地特征算法始终利用卷积神经网络（CNN）体系结构有限。此外，即使使用高性能的GPU设备，局部特征的计算效率也不令人满意。在本文中，我们通过提出基于CNN的本地功能算法来解决此类问题。所提出的方法引入了一个全局增强模块，以在轻质网络中融合全局视觉线索，然后从新颖的深度强化学习方案从本地功能匹配任务的角度通过新颖的深度强化学习方案进行优化。公共基准的实验表明，该提案可以针对视觉干扰实现相当大的鲁棒性，同时实时进行。
Local feature provides compact and invariant image representation for various visual tasks. Current deep learning-based local feature algorithms always utilize convolution neural network (CNN) architecture with limited receptive field. Besides, even with high-performance GPU devices, the computational efficiency of local features cannot be satisfactory. In this paper, we tackle such problems by proposing a CNN-based local feature algorithm. The proposed method introduces a global enhancement module to fuse global visual clues in a light-weight network, and then optimizes the network by novel deep reinforcement learning scheme from the perspective of local feature matching task. Experiments on the public benchmarks demonstrate that the proposal can achieve considerable robustness against visual interference and meanwhile run in real time.
