arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07034cs.CV
收藏

视频序列无监督对象表示的基准测试

Benchmarking Unsupervised Object Representations for Video Sequences

University of Göttingen(哥廷根大学);University of Tübingen(蒂宾根大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Bernstein Center for Computational Neuroscience(伯恩斯坦计算神经科学中心);Campus Institute Data Science(校园数据科学研究所);Max Planck Institute for Dynamics and Self-Organization(马克斯·普朗克动力学与自组织研究所)

Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker

摘要:

以物体的形式感知世界并通过时间跟踪它们是推理和场景理解的关键先决条件。最近,已经提出了几种方法用于对象中心表示的无监督学习。然而,由于这些模型是在不同的下游任务中进行评估的,因此目前还不清楚它们在基本感知能力(如检测,图形-背景分割和跟踪对象)方面的比较情况。为了缩小这一差距,我们设计了一个基准测试,其中包含四个不同复杂度的数据集和七个额外的测试集,这些测试集具有与自然视频相关的具有挑战性的跟踪场景。使用这个基准测试,我们比较了四种以对象为中心的方法的感知能力:ViMON,MONet的视频扩展,基于经常性的空间注意力,OP 3,通过空间混合模型利用聚类,以及TBA和SCALOR,通过空间Transformers使用显式因子分解。我们的研究结果表明,与无约束的潜在表示的架构学习更强大的表示在目标检测,分割和跟踪方面比空间Transformer为基础的架构。我们还观察到,没有一种方法能够优雅地处理最具挑战性的跟踪场景,尽管它们的合成性质,这表明我们的基准可以提供富有成效的指导,学习更强大的以对象为中心的视频表示。

英文摘要:

Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric representations. However, since these models were evaluated on different downstream tasks, it remains unclear how they compare in terms of basic perceptual abilities such as detection, figure-ground segmentation and tracking of objects. To close this gap, we design a benchmark with four data sets of varying complexity and seven additional test sets featuring challenging tracking scenarios relevant for natural videos. Using this benchmark, we compare the perceptual abilities of four object-centric approaches: ViMON, a video-extension of MONet, based on recurrent spatial attention, OP3, which exploits clustering via spatial mixture models, as well as TBA and SCALOR, which use explicit factorization via spatial transformers. Our results suggest that the architectures with unconstrained latent representations learn more powerful representations in terms of object detection, segmentation and tracking than the spatial transformer based architectures. We also observe that none of the methods are able to gracefully handle the most challenging tracking scenarios despite their synthetic nature, suggesting that our benchmark may provide fruitful guidance towards learning more robust object-centric video representations.

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。

↑