arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.03049cs.CVcs.LG
收藏

Meta-Tracker:快速和鲁棒的视觉对象跟踪器在线适配

Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers

Department of Computer Science, University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校计算机科学系)

Eunbyung Park, Alexander C. Berg

摘要:

本文改进了使用在线自适应的最先进的视觉对象跟踪器。我们的核心贡献是一种基于离线元学习的方法,用于调整在线自适应跟踪中使用的初始深度网络。Meta学习由深度网络的目标驱动,可以快速适应未来帧中的特定目标。理想情况下,生成的模型将重点放在对未来帧有用的特征上,并避免过度拟合背景杂波、目标的小部分或噪声。通过在元学习过程中强制执行少量的更新迭代,最终的网络训练速度明显更快。我们证明了这种方法的高性能跟踪方法的顶部:跟踪检测为基础的MDNet和相关性为基础的CREST。在标准基准测试OTB 2015和VOT 2016上的实验结果表明,我们的两种跟踪器的元学习版本提高了速度、准确性和鲁棒性。

英文摘要:

This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta learning is driven by the goal of deep networks that can quickly be adapted to robustly model a particular target in future frames. Ideally the resulting models focus on features that are useful for future frames, and avoid overfitting to background clutter, small parts of the target, or noise. By enforcing a small number of update iterations during meta-learning, the resulting networks train significantly faster. We demonstrate this approach on top of the high performance tracking approaches: tracking-by-detection based MDNet and the correlation based CREST. Experimental results on standard benchmarks, OTB2015 and VOT2016, show that our meta-learned versions of both trackers improve speed, accuracy, and robustness.

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。

↑