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 1702.08513cs.CVcs.DBcs.LGcs.RO
收藏

从嘈杂的Web数据中学习深度视觉对象模型:如何使其工作

Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work

Sapienza Rome University(罗马一大(萨皮恩扎罗马大学));University of Birmingham(伯明翰大学);Department of Computer, Control and Management Engineering(计算机、控制与管理工程系)

Nizar Massouh, Francesca Babiloni, Tatiana Tommasi, Jay Young, Nick Hawes, Barbara Caputo

摘要:

深度网络在大规模数据汇集上训练时蓬勃发展。这使得ImageNet在视觉对象分类的深度架构开发中发挥了核心作用。然而,ImageNet是在特定的时间段内创建的,因此它容易老化,以及数据集偏差问题。超越固定的训练数据集将导致更强大的视觉系统,特别是当部署在新环境中的机器人上时,这些机器人必须对它们在那里遇到的物体进行训练。为了实现这一点,摆脱对手动注释器的需求是很重要的。最近的工作已经开始研究如何使用大量的图像在Web上可用的地方手动图像注释。我们通过两个发现为这一研究线索做出了贡献:(1)一项研究将给定水平的噪声标签与两种不同类型噪声的两种深度架构的预期准确性下降相关联,该研究清楚地将GoogLeNet确定为从Web数据中学习的合适架构;(2)基于视觉和自然语言处理概念扩展策略,创建具有最小噪声和最大视觉可变性的Web数据集的配方。通过结合这两个结果,我们获得了一种从Web自动学习强大的深度对象模型的方法。我们确认我们的方法的有效性,通过对象分类实验,使用我们的Web衍生版本的ImageNet上流行的机器人视觉基准数据库,并在移动机器人上的终身对象发现任务。

英文摘要:

Deep networks thrive when trained on large scale data collections. This has given ImageNet a central role in the development of deep architectures for visual object classification. However, ImageNet was created during a specific period in time, and as such it is prone to aging, as well as dataset bias issues. Moving beyond fixed training datasets will lead to more robust visual systems, especially when deployed on robots in new environments which must train on the objects they encounter there. To make this possible, it is important to break free from the need for manual annotators. Recent work has begun to investigate how to use the massive amount of images available on the Web in place of manual image annotations. We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy. By combining these two results, we obtain a method for learning powerful deep object models automatically from the Web. We confirm the effectiveness of our approach through object categorization experiments using our Web-derived version of ImageNet on a popular robot vision benchmark database, and on a lifelong object discovery task on a mobile robot.

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。

↑