论文标题
相同的特征，不同的一天：季节性不变性的弱监督功能学习
Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance
论文作者
论文摘要
“像白天和黑夜”是一种常用的表达方式，暗示两件事是完全不同的。不幸的是，在不同季节或一天中的不同季节，同一场景的当前视觉特征表示往往是这种情况。本文的目的是提供一个密集的特征表示形式，可用于执行本地化，稀疏匹配或图像检索，无论当前的季节性或时间外观如何。 最近，已经提出了几种提议的深度学习密集特征表示方法。这些方法利用图像对之间的地面真像素对应关系，并专注于特征的空间特性。因此，它们无法解决时间或季节性变化。此外，在大多数情况下，在跨季节环境中获得所需像素的对应数据进行训练是非常复杂的。 我们提出了Deja-vu，这是一种弱监督的学习季节不变特征的方法，不需要像素的地面真相数据。所提出的系统仅需要粗标签，指示两个图像是否对应于同一位置。从这些标签中，尽管环境发生了变化，但对网络进行了训练，可以为相应位置生成“相似”的特征图。代码将在以下网址提供：https：//github.com/jspenmar/dejavu_features
"Like night and day" is a commonly used expression to imply that two things are completely different. Unfortunately, this tends to be the case for current visual feature representations of the same scene across varying seasons or times of day. The aim of this paper is to provide a dense feature representation that can be used to perform localization, sparse matching or image retrieval, regardless of the current seasonal or temporal appearance. Recently, there have been several proposed methodologies for deep learning dense feature representations. These methods make use of ground truth pixel-wise correspondences between pairs of images and focus on the spatial properties of the features. As such, they don't address temporal or seasonal variation. Furthermore, obtaining the required pixel-wise correspondence data to train in cross-seasonal environments is highly complex in most scenarios. We propose Deja-Vu, a weakly supervised approach to learning season invariant features that does not require pixel-wise ground truth data. The proposed system only requires coarse labels indicating if two images correspond to the same location or not. From these labels, the network is trained to produce "similar" dense feature maps for corresponding locations despite environmental changes. Code will be made available at: https://github.com/jspenmar/DejaVu_Features
