arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.09593cs.CV
收藏

从纪录片中发现和学习新对象

Discover and Learn New Objects from Documentaries

The Chinese University of Hong Kong(香港中文大学)

Kai Chen, Hang Song, Chen Change Loy, Dahua Lin

摘要:

尽管近年来取得了显著的进展,但在新的背景下检测对象仍然是一项具有挑战性的任务。从公共数据集学习的检测器只能使用固定的类别列表,而从头开始训练通常需要大量带有详细注释的训练数据。这项工作旨在探索一种新的方法-以弱监督的方式从纪录片中学习对象检测器。这是受到观察的启发,即纪录片经常提供特定对象类别的专门阐述,其中视觉呈现与字幕对齐。我们相信物体探测器可以从如此丰富的信息源中学习。为了实现这一目标,我们开发了一个联合概率框架,其中包括视频帧和字幕在内的各条信息通过视觉和语言链接汇集在一起。在此基础上,我们进一步推导出一个弱监督学习算法,其中对象模型学习和训练集挖掘统一在一个优化过程中。在真实世界数据集上的实验结果表明,这是一种有效的方法来学习新的对象检测器。

英文摘要:

Despite the remarkable progress in recent years, detecting objects in a new context remains a challenging task. Detectors learned from a public dataset can only work with a fixed list of categories, while training from scratch usually requires a large amount of training data with detailed annotations. This work aims to explore a novel approach -- learning object detectors from documentary films in a weakly supervised manner. This is inspired by the observation that documentaries often provide dedicated exposition of certain object categories, where visual presentations are aligned with subtitles. We believe that object detectors can be learned from such a rich source of information. Towards this goal, we develop a joint probabilistic framework, where individual pieces of information, including video frames and subtitles, are brought together via both visual and linguistic links. On top of this formulation, we further derive a weakly supervised learning algorithm, where object model learning and training set mining are unified in an optimization procedure. Experimental results on a real world dataset demonstrate that this is an effective approach to learning new object detectors.

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。

↑