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 2009.11044cs.CVcs.AIcs.LGcs.RO
收藏

事件数据的无监督特征学习:正问题与反问题公式化

Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation

University of Zurich(苏黎世大学)

Dimche Kostadinov, Davide Scaramuzza

摘要:

基于事件的相机记录每个像素亮度变化的异步流。因此,与标准的基于帧的相机相比,它们具有许多优点,包括高时间分辨率、高动态范围和无运动模糊。由于事件数据的异步性质,高效学习事件数据的紧凑表示是具有挑战性的。虽然它仍然没有探索的空间和时间事件的“信息”是有用的模式识别任务的程度。在本文中,我们专注于单层架构。我们分析了两个一般问题配方的性能:直接和逆,从本地事件数据(在时空中描述的事件的本地卷)的无监督特征学习。我们确定并显示每种方法的主要优势。理论上,我们分析了最优解的保证,异步的可能性,并行参数更新,和计算复杂性。我们提出了物体识别的数值实验。我们评估下的正问题和反问题的解决方案,并与国家的最先进的方法进行比较。我们的实证结果突出了这两种方法的优势,从事件数据的表示学习。与同类方法中最先进的方法相比,我们的识别准确率提高了9%。

英文摘要:

Event-based cameras record an asynchronous stream of per-pixel brightness changes. As such, they have numerous advantages over the standard frame-based cameras, including high temporal resolution, high dynamic range, and no motion blur. Due to the asynchronous nature, efficient learning of compact representation for event data is challenging. While it remains not explored the extent to which the spatial and temporal event "information" is useful for pattern recognition tasks. In this paper, we focus on single-layer architectures. We analyze the performance of two general problem formulations: the direct and the inverse, for unsupervised feature learning from local event data (local volumes of events described in space-time). We identify and show the main advantages of each approach. Theoretically, we analyze guarantees for an optimal solution, possibility for asynchronous, parallel parameter update, and the computational complexity. We present numerical experiments for object recognition. We evaluate the solution under the direct and the inverse problem and give a comparison with the state-of-the-art methods. Our empirical results highlight the advantages of both approaches for representation learning from event data. We show improvements of up to 9 % in the recognition accuracy compared to the state-of-the-art methods from the same class of methods.

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。

↑