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 2311.04414cs.CV
收藏

学习视频对象分割中标注的“什么”与“如何”

Learning the What and How of Annotation in Video Object Segmentation

Technical University of Denmark(丹麦技术大学);Pioneer Center for AI(先锋人工智能中心);LIX, Ecole Polytechnique, CNRS, Institut Polytechnique de Paris(巴黎综合理工学院计算机科学实验室,法国国家科学研究中心,巴黎综合理工学院,巴黎理工学院)

Thanos Delatolas, Vicky Kalogeiton, Dim P. Papadopoulos

AI总结:

提出EVA-VOS人机协同标注框架,通过智能体迭代预测标注帧与类型,在MOSE和DAVIS数据集上实现接近人工精度的掩码,标注速度提升3.5倍。

摘要:

视频对象分割(VOS)对从视频编辑到视频数据生成的多种应用至关重要。训练VOS模型需要大量人工标注的训练视频。传统上,对象标注的标准方式要求人类在每帧视频中为目标对象绘制详细的分割掩码。然而,这种标注过程既繁琐又耗时。为降低标注成本,本文提出EVA-VOS,一种用于视频对象分割的人机协同标注框架。与传统方法不同,我们引入一个智能体,它迭代地预测要标注的帧(“什么”)以及使用的标注类型(“如何”)。然后,标注者仅标注被选中的帧,用于更新VOS模块,从而在标注时间上带来显著收益。我们在MOSE和DAVIS数据集上进行实验,结果表明:(a)EVA-VOS生成的掩码准确度接近人工一致性,且比标准视频标注方式快3.5倍;(b)我们的帧选择达到了最先进的性能;(c)与所有其他方法和基线相比,EVA-VOS在标注时间方面取得了显著的性能提升。

英文摘要:

Video Object Segmentation (VOS) is crucial for several applications, from video editing to video data generation. Training a VOS model requires an abundance of manually labeled training videos. The de-facto traditional way of annotating objects requires humans to draw detailed segmentation masks on the target objects at each video frame. This annotation process, however, is tedious and time-consuming. To reduce this annotation cost, in this paper, we propose EVA-VOS, a human-in-the-loop annotation framework for video object segmentation. Unlike the traditional approach, we introduce an agent that predicts iteratively both which frame ("What") to annotate and which annotation type ("How") to use. Then, the annotator annotates only the selected frame that is used to update a VOS module, leading to significant gains in annotation time. We conduct experiments on the MOSE and the DAVIS datasets and we show that: (a) EVA-VOS leads to masks with accuracy close to the human agreement 3.5x faster than the standard way of annotating videos; (b) our frame selection achieves state-of-the-art performance; (c) EVA-VOS yields significant performance gains in terms of annotation time compared to all other methods and baselines.

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。

↑