Abstract
Deep metric learning aims to learn an embedding function, modeled as deep neural network. This embedding function usually puts semantically similar images close while dissimilar images far from each other in the learned embedding space. Recently, ensemble has been applied to deep metric learning to yield state-of-the-art results. As one important aspect of ensemble, the learners should be diverse in their feature embeddings. To this end, we propose an attention-based ensemble, which uses multiple attention masks, so that each learner can attend to different parts of the object. We also propose a divergence loss, which encourages diversity among the learners. The proposed method is applied to the standard benchmarks of deep metric learning and experimental results show that it outperforms the state-of-the-art methods by a significant margin on image retrieval tasks.
Abstract (translated)
深度量度学习旨在学习嵌入函数,建模为深度神经网络。这种嵌入功能通常将语义相似的图像放在一起,而在学习的嵌入空间中,相似的图像彼此远离。最近,ensemble已应用于深度度量学习,以产生最先进的结果。作为整体的一个重要方面,学习者应该在其特征嵌入中具有多样性。为此,我们提出了一种基于注意力的集合,它使用多个注意力掩模,以便每个学习者可以照顾对象的不同部分。我们还提出了分歧损失,鼓励学习者之间的多样性。所提出的方法应用于深度量学习的标准基准,实验结果表明,它在图像检索任务上显着优于最先进的方法。
URL
https://arxiv.org/abs/1804.00382