arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.02898cs.CV
收藏

端到端实例边缘检测

End-to-End Instance Edge Detection

University of Wisconsin–Madison(威斯康星大学麦迪逊分校)

Xueyan Zou, Haotian Liu, Yong Jae Lee

摘要:

边缘检测一直是计算机视觉领域的一个重要问题。以前的工作已经探索了类别不可知或类别感知的边缘检测。在本文中,我们将探讨在对象实例的背景下的边缘检测。虽然对象边界可以很容易地从分割掩模中导出,但在实践中,实例分割模型被训练为最大化到地面实况掩模的IoU,这意味着分割边界没有被强制与地面实况边缘边界精确对齐。因此,实例边缘检测本身的任务是不同的和关键的。由于精确的边缘检测需要高分辨率的特征图,我们设计了一种新的Transformer架构,有效地结合了FPN和Transformer解码器,使交叉关注多尺度的高分辨率特征图在一个合理的计算预算。此外,我们提出了一个轻量级的密集预测头,适用于实例边缘和掩模检测。最后,我们使用减少焦点损失的惩罚来有效地训练模型,在实例边缘上具有点监督,这可以减少注释成本。与最先进的基线相比,我们展示了极具竞争力的实例边缘检测性能,并且还表明所提出的任务和损失与实例分割和目标检测是互补的。

英文摘要:

Edge detection has long been an important problem in the field of computer vision. Previous works have explored category-agnostic or category-aware edge detection. In this paper, we explore edge detection in the context of object instances. Although object boundaries could be easily derived from segmentation masks, in practice, instance segmentation models are trained to maximize IoU to the ground-truth mask, which means that segmentation boundaries are not enforced to precisely align with ground-truth edge boundaries. Thus, the task of instance edge detection itself is different and critical. Since precise edge detection requires high resolution feature maps, we design a novel transformer architecture that efficiently combines a FPN and a transformer decoder to enable cross attention on multi-scale high resolution feature maps within a reasonable computation budget. Further, we propose a light weight dense prediction head that is applicable to both instance edge and mask detection. Finally, we use a penalty reduced focal loss to effectively train the model with point supervision on instance edges, which can reduce annotation costs. We demonstrate highly competitive instance edge detection performance compared to state-of-the-art baselines, and also show that the proposed task and loss are complementary to instance segmentation and object detection.

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。

↑