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 1802.08833cs.CVcs.RO
收藏

通过视觉域定位的自适应深度学习

Adaptive Deep Learning through Visual Domain Localization

VANDAL Laboratory, Department of Computer, Management and Control Engineering (DIAG), Sapienza Rome University(VANDAL实验室,计算机、管理与控制工程系(DIAG),罗马萨皮恩扎大学);Italian Institute of Technology(意大利理工学院)

Gabriele Angeletti, Barbara Caputo, Tatiana Tommasi

摘要:

一个商业机器人,由其制造商训练,以识别预定义的数量和类型的对象,可能会在许多设置中使用,这将在一般情况下不同的照明条件,背景,类型和程度的杂波,等等。最近的计算机视觉作品解决这个泛化问题,通过领域自适应方法,假设训练系统的视觉域作为源,部署域作为目标。所有的方法都假设在训练过程中可以访问所有类别的目标图像,这在机器人应用中是不现实的。我们解决这个问题,提出了一种算法,考虑到机器人视觉的具体需求。我们的直觉是,在机器人技术中经历的领域转移的本质是局部的。我们通过学习映射来利用这一点,这些映射在空间上将域接地并量化移位的程度,嵌入到端到端的深度领域自适应架构中。通过显式地定位域偏移的根,我们显着减少了要调整的架构参数的数量,我们获得了在训练时处理目标域中类别子集所需的灵活性,并且我们提供了关于任何分类决策背后的基本原理的明确反馈,这可以在人机交互中利用。两个不同的设置的iCub世界数据库上的实验证实了我们的方法对机器人视觉的适用性。

英文摘要:

A commercial robot, trained by its manufacturer to recognize a predefined number and type of objects, might be used in many settings, that will in general differ in their illumination conditions, background, type and degree of clutter, and so on. Recent computer vision works tackle this generalization issue through domain adaptation methods, assuming as source the visual domain where the system is trained and as target the domain of deployment. All approaches assume to have access to images from all classes of the target during training, an unrealistic condition in robotics applications. We address this issue proposing an algorithm that takes into account the specific needs of robot vision. Our intuition is that the nature of the domain shift experienced mostly in robotics is local. We exploit this through the learning of maps that spatially ground the domain and quantify the degree of shift, embedded into an end-to-end deep domain adaptation architecture. By explicitly localizing the roots of the domain shift we significantly reduce the number of parameters of the architecture to tune, we gain the flexibility necessary to deal with subset of categories in the target domain at training time, and we provide a clear feedback on the rationale behind any classification decision, which can be exploited in human-robot interactions. Experiments on two different settings of the iCub World database confirm the suitability of our method for robot vision.

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。

↑