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 2212.13445cs.CV
收藏

注入对齐真实和预测片段的最常用方式

The most general manner to injectively align true and predicted segments

University of Amsterdam(阿姆斯特丹大学)

Maarten Marx

摘要:

Kirilov et al(2019)开发了一种称为Panoptic Quality(PQ)的指标,用于评估图像分割方法。该度量基于混淆表,并将预测分割与地面实况分割进行比较。该比较中唯一不直接的部分是对齐两个分割中的片段。只有当对齐是部分双射时,度量才能很好地工作。Kirilov et al(2019)列出了比对定义的3个理想属性:它应该是简单的,可解释的和可有效计算的。有许多定义保证部分双射和这3个性质。我们提出了最弱的:一个既充分又必要的,以保证对齐是一个部分双射。这种新的条件是有效的可计算的和自然的。它简单地说,正确预测的元素(在图像分割中,像素)的数量应该大于错过的数量,并且大于虚假元素的数量。这严格弱于Kirilov et al(2019)的提议。在公式中,代替|TP| >| FN \textbar| + |FP|,较弱的条件要求|TP| > |FN|和|TP| > |FP|。我们评估新的对齐条件理论和经验。

英文摘要:

Kirilov et al (2019) develop a metric, called Panoptic Quality (PQ), to evaluate image segmentation methods. The metric is based on a confusion table, and compares a predicted to a ground truth segmentation. The only non straightforward part in this comparison is to align the segments in the two segmentations. A metric only works well if that alignment is a partial bijection. Kirilov et al (2019) list 3 desirable properties for a definition of alignment: it should be simple, interpretable and effectively computable. There are many definitions guaranteeing a partial bijection and these 3 properties. We present the weakest: one that is both sufficient and necessary to guarantee that the alignment is a partial bijection. This new condition is effectively computable and natural. It simply says that the number of correctly predicted elements (in image segmentation, the pixels) should be larger than the number of missed, and larger than the number of spurious elements. This is strictly weaker than the proposal in Kirilov et al (2019). In formulas, instead of |TP|> |FN\textbar| + |FP|, the weaker condition requires that |TP|> |FN| and |TP| > |FP|. We evaluate the new alignment condition theoretically and empirically.

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。

↑