论文标题
太阳能：图像检索的二阶损失和注意力
SOLAR: Second-Order Loss and Attention for Image Retrieval
论文作者
论文摘要
深度学习的最新作品表明，二阶信息在许多计算机视觉任务中都是有益的。可以在空间上下文和抽象特征维度上执行二阶信息。在这项工作中，我们探索了两个二阶组件。一个专注于二阶空间信息，以提高本地和全局图像描述符的性能。它用于重新体重特征地图，因此强调了随后用于描述的显着图像位置。第二个组件与二阶相似性（SOS）损失有关，我们将其扩展到全局描述符以进行图像检索，并用于通过硬性挖掘来增强三重态损失。我们在两个不同的任务和数据集上验证方法，以进行图像检索和图像匹配。结果表明，我们的两个二阶组件相互补充，在任务上带来了重大的性能提高，并在公共基准中带来了最新的结果。代码可用：http：//github.com/tonyngjichun/solar
Recent works in deep-learning have shown that second-order information is beneficial in many computer-vision tasks. Second-order information can be enforced both in the spatial context and the abstract feature dimensions. In this work, we explore two second-order components. One is focused on second-order spatial information to increase the performance of image descriptors, both local and global. It is used to re-weight feature maps, and thus emphasise salient image locations that are subsequently used for description. The second component is concerned with a second-order similarity (SOS) loss, that we extend to global descriptors for image retrieval, and is used to enhance the triplet loss with hard-negative mining. We validate our approach on two different tasks and datasets for image retrieval and image matching. The results show that our two second-order components complement each other, bringing significant performance improvements in both tasks and lead to state-of-the-art results across the public benchmarks. Code available at: http://github.com/tonyngjichun/SOLAR
