论文标题
暗黑破坏神：基于字典的注意力块，用于深度度量学习
DIABLO: Dictionary-based Attention Block for Deep Metric Learning
论文作者
论文摘要
在对看不见的课程的表示方面的最新突破和示例是在深度度量学习中通过培训与图像表示形式以及具有深网络的相应指标。最近的贡献主要针对培训部分（损失功能，抽样策略等），而少数作品则集中于提高图像表示的判别能力。在本文中，我们提出了暗黑破坏神，这是一种基于字典的注意力嵌入方法。暗黑破坏神通过仅将视觉相关的功能汇总在一起，同时比深度度量学习中的其他基于注意力的方法更容易训练，从而产生更丰富的表示。这是在四个深度度量学习数据集（CUB-200-2011，CARS-196，Stanford Online Products和Shop Cloth Cloth Calliv的）上实验证实的，暗黑破坏神展示了最先进的表演。
Recent breakthroughs in representation learning of unseen classes and examples have been made in deep metric learning by training at the same time the image representations and a corresponding metric with deep networks. Recent contributions mostly address the training part (loss functions, sampling strategies, etc.), while a few works focus on improving the discriminative power of the image representation. In this paper, we propose DIABLO, a dictionary-based attention method for image embedding. DIABLO produces richer representations by aggregating only visually-related features together while being easier to train than other attention-based methods in deep metric learning. This is experimentally confirmed on four deep metric learning datasets (Cub-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval) for which DIABLO shows state-of-the-art performances.
