arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.16562cs.CV
收藏

Boundary IoU:改进以对象为中心的图像分割评价

Boundary IoU: Improving Object-Centric Image Segmentation Evaluation

UIUC(伊利诺伊大学厄巴纳-香槟分校);Facebook AI Research (FAIR)(Facebook人工智能研究院)

Bowen Cheng, Ross Girshick, Piotr Dollár, Alexander C. Berg, Alexander Kirillov

摘要:

我们提出了边界IoU(Intersection-over-Union),这是一种新的分割评估方法,专注于边界质量。我们对不同的错误类型和对象大小进行了广泛的分析,并表明边界IoU对大型对象的边界错误比标准的Mask IoU测量更敏感,并且不会过度惩罚较小对象的错误。新的质量测量显示了几个理想的特性,如对称性w.r.t.预测/地面真值对和跨尺度的平衡响应,这使得它比其他以边界为中心的度量(如Trimap IoU和F-measure)更适合于分割评估。基于边界IoU,我们分别通过提出边界AP(平均精度)和边界PQ(全景质量)度量来更新实例和全景分割任务的标准评估协议。我们的实验表明,新的评估指标跟踪边界质量的改善,通常被忽视的当前掩模IoU为基础的评估指标。我们希望,采用新的边界敏感的评价指标将导致快速进步的分割方法,提高边界质量。

英文摘要:

We present Boundary IoU (Intersection-over-Union), a new segmentation evaluation measure focused on boundary quality. We perform an extensive analysis across different error types and object sizes and show that Boundary IoU is significantly more sensitive than the standard Mask IoU measure to boundary errors for large objects and does not over-penalize errors on smaller objects. The new quality measure displays several desirable characteristics like symmetry w.r.t. prediction/ground truth pairs and balanced responsiveness across scales, which makes it more suitable for segmentation evaluation than other boundary-focused measures like Trimap IoU and F-measure. Based on Boundary IoU, we update the standard evaluation protocols for instance and panoptic segmentation tasks by proposing the Boundary AP (Average Precision) and Boundary PQ (Panoptic Quality) metrics, respectively. Our experiments show that the new evaluation metrics track boundary quality improvements that are generally overlooked by current Mask IoU-based evaluation metrics. We hope that the adoption of the new boundary-sensitive evaluation metrics will lead to rapid progress in segmentation methods that improve boundary quality.

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。

↑