arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.14724cs.CV
收藏

当少样本学习遇到视频目标检测时

When Few-Shot Learning Meets Video Object Detection

Wyze Labs, Inc.(Wyze实验室公司);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Zhejiang University(浙江大学);University of Rochester(罗切斯特大学)

Zhongjie Yu, Gaoang Wang, Lin Chen, Sebastian Raschka, Jiebo Luo

摘要:

与静态图像不同,视频包含额外的时间和空间信息,用于更好的目标检测。然而,获得大量具有受监督的深度学习所需的限界框注释的视频是昂贵的。虽然人类可以通过观看几个视频片段轻松地学会识别新物体,但深度学习通常会遇到过拟合问题。这就引出了一个重要的问题:如何有效地从几个标记的视频片段中学习视频对象检测器?本文研究了视频目标检测中的少样本学习问题。我们首先定义了Few-Shot设置,并为Few-Shot视频目标检测创建了一个新的基准数据集,该数据集来自广泛使用的ImageNet VID数据集。我们采用了一个迁移学习框架,有效地训练大量的基础类对象和一些视频剪辑的新类对象的视频对象检测器。通过分析在此框架下的两种方法(联合和冻结)在我们设计的弱基和强基数据集上的结果,我们发现了不足和过拟合问题。一个简单而有效的方法,称为解冻,自然发展权衡这两个问题,并验证我们的分析。在不同场景下对我们提出的基准数据集进行的广泛实验证明了我们的新型分析在这个新的少镜头视频Few-Shot对象检测问题中的有效性。目标检测问题。

英文摘要:

Different from static images, videos contain additional temporal and spatial information for better object detection. However, it is costly to obtain a large number of videos with bounding box annotations that are required for supervised deep learning. Although humans can easily learn to recognize new objects by watching only a few video clips, deep learning usually suffers from overfitting. This leads to an important question: how to effectively learn a video object detector from only a few labeled video clips? In this paper, we study the new problem of few-shot learning for video object detection. We first define the few-shot setting and create a new benchmark dataset for few-shot video object detection derived from the widely used ImageNet VID dataset. We employ a transfer-learning framework to effectively train the video object detector on a large number of base-class objects and a few video clips of novel-class objects. By analyzing the results of two methods under this framework (Joint and Freeze) on our designed weak and strong base datasets, we reveal insufficiency and overfitting problems. A simple but effective method, called Thaw, is naturally developed to trade off the two problems and validate our analysis. Extensive experiments on our proposed benchmark datasets with different scenarios demonstrate the effectiveness of our novel analysis in this new few-shot video object detection problem.

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。

↑