arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.01682cs.CV
收藏

带角度损失的深度度量学习

Deep Metric Learning with Angular Loss

Baidu Research(百度研究院)

Jian Wang, Feng Zhou, Shilei Wen, Xiao Liu, Yuanqing Lin

摘要:

现代图像搜索系统需要对图像进行语义理解,而学习一个好的度量图像之间相似性的度量是一个关键而尚未解决的问题。虽然深度度量学习通过从图像数据中提取高级抽象而产生了令人印象深刻的性能增益,但适当的客观损失函数成为提高性能的核心问题。在本文中,我们提出了一种新的角度损失,它考虑到角度关系,学习更好的相似性度量。鉴于以前的度量学习方法专注于优化图像对的相似性(对比损失)或相对相似性(三重损失),我们提出的方法旨在约束三重三角形负点的角度。与传统方法相比,观察到几个有利的性能。首先,引入尺度不变性,提高了目标对特征变化的鲁棒性。其次,本质上施加了三阶几何约束,捕获了比对比损失或三重态损失更多的三重态三角形的局部结构。第三,更好的收敛性已被证明在三个公开可用的数据集上的实验。

英文摘要:

The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images. While deep metric learning has yielded impressive performance gains by extracting high level abstractions from image data, a proper objective loss function becomes the central issue to boost the performance. In this paper, we propose a novel angular loss, which takes angle relationship into account, for learning better similarity metric. Whereas previous metric learning methods focus on optimizing the similarity (contrastive loss) or relative similarity (triplet loss) of image pairs, our proposed method aims at constraining the angle at the negative point of triplet triangles. Several favorable properties are observed when compared with conventional methods. First, scale invariance is introduced, improving the robustness of objective against feature variance. Second, a third-order geometric constraint is inherently imposed, capturing additional local structure of triplet triangles than contrastive loss or triplet loss. Third, better convergence has been demonstrated by experiments on three publicly available datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑