论文标题
改进硬网的描述符
Improving the HardNet Descriptor
论文作者
论文摘要
在论文中，我们考虑了局部特征描述符学习的问题，用于宽基线立体声，重点关注硬核描述符，该描述符接近最新。引入了AMOS Patches数据集，从而提高了照明和外观变化的鲁棒性。它基于来自AMOS数据集中选定摄像机的注册图像。我们提供有关补丁数据集创建过程的建议，并评估经过不同模式数据训练的硬网。我们还介绍了一种数据集组合和还原方法，该方法允许在较小的数据集中进行可比性的性能。 HardNet8始终优于原始硬网，从所做的架构选择中受益：连接性模式，最终池，接受场，通过手动或自动搜索算法找到的CNN构建块-Darts。我们显示了被忽视的超参数（例如批处理大小和训练时间长度）对描述符质量的影响。 PCA维度降低进一步提高了性能并减少记忆足迹。 最后，获得的见解导致了两个HardNet8描述：一个在各种基准上表现良好 - HPATCHES，AMOS PATCHES和IMW光效应，另一个针对IMW光仪进行了优化。
In the thesis we consider the problem of local feature descriptor learning for wide baseline stereo focusing on the HardNet descriptor, which is close to state-of-the-art. AMOS Patches dataset is introduced, which improves robustness to illumination and appearance changes. It is based on registered images from selected cameras from the AMOS dataset. We provide recommendations on the patch dataset creation process and evaluate HardNet trained on data of different modalities. We also introduce a dataset combination and reduction methods, that allow comparable performance on a significantly smaller dataset. HardNet8, consistently outperforming the original HardNet, benefits from the architectural choices made: connectivity pattern, final pooling, receptive field, CNN building blocks found by manual or automatic search algorithms -- DARTS. We show impact of overlooked hyperparameters such as batch size and length of training on the descriptor quality. PCA dimensionality reduction further boosts performance and also reduces memory footprint. Finally, the insights gained lead to two HardNet8 descriptors: one performing well on a variety of benchmarks -- HPatches, AMOS Patches and IMW Phototourism, the other is optimized for IMW Phototourism.
