arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.09083cs.CV
收藏

自适应SVM +：利用已存储信息进行学习以实现领域自适应

Adaptive SVM+: Learning with Privileged Information for Domain Adaptation

Computational Biomedicine Lab, University of Houston（休斯顿大学计算生物医学实验室）

Nikolaos Sarafianos, Michalis Vrigkas, Ioannis A. Kakadiaris

备注：
To appear in ICCV Workshops 2017 (TASK-CV)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

在学习过程中增加额外的知识对于一些计算机视觉和机器学习任务是有益的。特权信息是源自适应于目标域的源域，还是作为仅在训练时可用的附加特征，使用这样的特权（即，辅助）信息是非常重要的，因为它提高了识别性能和推广。然而，主要信息和特权信息很少来自同一分布，这对识别任务提出了额外的挑战。为了解决这些挑战，我们提出了一种新的学习范式，利用特权信息的领域自适应设置执行视觉识别任务。建议的框架，名为自适应SVM+，结合了使用特权信息（LUPI）的学习范式和领域自适应框架，这是自然嵌入在一个定期SVM的目标函数的优点。我们证明了我们的方法的有效性，公开可用的动物属性和交互数据集，并报告在这两个国家的最先进的结果。

英文摘要：

Incorporating additional knowledge in the learning process can be beneficial for several computer vision and machine learning tasks. Whether privileged information originates from a source domain that is adapted to a target domain, or as additional features available at training time only, using such privileged (i.e., auxiliary) information is of high importance as it improves the recognition performance and generalization. However, both primary and privileged information are rarely derived from the same distribution, which poses an additional challenge to the recognition task. To address these challenges, we present a novel learning paradigm that leverages privileged information in a domain adaptation setup to perform visual recognition tasks. The proposed framework, named Adaptive SVM+, combines the advantages of both the learning using privileged information (LUPI) paradigm and the domain adaptation framework, which are naturally embedded in the objective function of a regular SVM. We demonstrate the effectiveness of our approach on the publicly available Animals with Attributes and INTERACT datasets and report state-of-the-art results in both of them.

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。

↑