arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.12977cs.CV
收藏

深度度量学习的可视化解释

Visual Explanation for Deep Metric Learning

Center for Research in Computer Vision, University of Central Florida(中佛罗里达大学计算机视觉研究中心)

Sijie Zhu, Taojiannan Yang, Chen Chen

摘要:

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,度量学习近年来受到了广泛的关注,但度量学习模型的解释却没有分类模型那么好。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部署到大范围的度量学习应用程序,并为理解模型提供了有价值的信息。此外,我们的实验表明,它的有效性在两个潜在的应用,即跨视图模式发现和交互式检索。源代码可从\url{https://github.com/Jeff-Zilence/Explain_Metric_Learning}获得。

英文摘要:

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 such 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 deployed to a large range of metric learning applications and provides valuable information for understanding the model. Furthermore, our experiments show its effectiveness on two potential applications, i.e. cross-view pattern discovery and interactive retrieval. The source code is available at \url{https://github.com/Jeff-Zilence/Explain_Metric_Learning}.

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。

↑