arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.05787cs.CV
收藏

目标检测中的平移等方差

Shift Equivariance in Object Detection

TomTom

Marco Manfredi, Yu Wang

摘要:

对小图像平移的鲁棒性是对象检测器的高度期望的性质。然而,最近的研究表明,基于CNN的分类器不是平移不变的。目前还不清楚这会在多大程度上影响目标检测,主要是因为两者之间的架构差异以及现代检测器预测空间的维度。为了评估端到端的目标检测模型的移位等方差,在本文中,我们提出了一个评价指标,建立在一个贪婪的搜索上下限的平均精度的移动图像集。我们的新度量表明,现代目标检测架构,无论是一级或两级,基于锚点或无锚点,即使是一个像素的输入图像偏移敏感。此外,我们研究了这个问题的几种可能的解决方案,无论是从文献和新提出的,量化的有效性,建议的度量。我们的结果表明,这些方法都不能提供全移位等方差。测量和分析不同模型的偏移方差的程度以及可能因素的贡献,是能够设计减轻甚至利用这种可变性的方法的第一步。

英文摘要:

Robustness to small image translations is a highly desirable property for object detectors. However, recent works have shown that CNN-based classifiers are not shift invariant. It is unclear to what extent this could impact object detection, mainly because of the architectural differences between the two and the dimensionality of the prediction space of modern detectors. To assess shift equivariance of object detection models end-to-end, in this paper we propose an evaluation metric, built upon a greedy search of the lower and upper bounds of the mean average precision on a shifted image set. Our new metric shows that modern object detection architectures, no matter if one-stage or two-stage, anchor-based or anchor-free, are sensitive to even one pixel shift to the input images. Furthermore, we investigate several possible solutions to this problem, both taken from the literature and newly proposed, quantifying the effectiveness of each one with the suggested metric. Our results indicate that none of these methods can provide full shift equivariance. Measuring and analyzing the extent of shift variance of different models and the contributions of possible factors, is a first step towards being able to devise methods that mitigate or even leverage such variabilities.

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。

↑