Visual Explanation for Deep Metric Learning
Visual Explanation for Deep Metric Learning
复制标题
DOI：
10.1109/tip.2021.3107214
复制
发表时间：
2019-09
影响因子：
10.6
通讯作者：
Sijie Zhu;Taojiannan Yang;Chen Chen-Chen
中科院分区：
文献类型：
--
作者：
Sijie Zhu;Taojiannan Yang;Chen Chen-Chen
这项工作探索了深度度量学习及其应用的视觉解释。作为学习表示的一个重要问题，度量学习近年来引起了人们的广泛关注，但度量学习模型的解释却没有分类那么好。为此，我们提出了一个直观的想法，通过分解最终激活来显示对两个输入图像的整体相似性贡献最大的地方。而不是只提供每个图像的整体激活图，我们建议生成两个图像之间的点到点激活强度，使不同区域之间的关系被揭露。我们表明，所提出的框架可以直接应用于广泛的度量学习应用程序，并提供了有价值的信息模型理解。理论和实证分析证明了所提出的整体激活图优于现有的方法。此外，我们的实验验证了所提出的点特定的激活地图上的两个应用程序，即跨视图模式发现和交互式检索的有效性。代码可在https://github.com/Jeff-Zilence/Explain_Metric_Learning上获得
This work explores the visual explanation for deep metric learning and its applications. As an important problem for learning representation, metric learning has attracted much attention recently, while the interpretation of the metric learning model is not as well-studied as classification. To this end, we propose an intuitive idea to show where contributes the most to the overall similarity of two input images by decomposing the final activation. Instead of only providing the overall activation map of each image, we propose to generate point-to-point activation intensity between two images so that the relationship between different regions is uncovered. We show that the proposed framework can be directly applied to a wide range of metric learning applications and provides valuable information for model understanding. Both theoretical and empirical analyses are provided to demonstrate the superiority of the proposed overall activation map over existing methods. Furthermore, our experiments validate the effectiveness of the proposed point-specific activation map on two applications, i.e. cross-view pattern discovery and interactive retrieval. Code is available at https://github.com/Jeff-Zilence/Explain_Metric_Learning