Detecting edges in images suffers from the problems of (P1) heavy imbalance between positive and negative classes as well as (P2) label uncertainty owing to disagreement between different annotators. Existing solutions address P1 using class-balanced cross-entropy loss and dice loss and P2 by only predicting edges agreed upon by most annotators. In this paper, we propose RankED, a unified ranking-based approach that addresses both the imbalance problem (P1) and the uncertainty problem (P2). RankED tackles these two problems with two components: One component which ranks positive pixels over negative pixels, and the second which promotes high confidence edge pixels to have more label certainty. We show that RankED outperforms previous studies and sets a new state-of-the-art on NYUD-v2, BSDS500 and Multi-cue datasets. Code is available at https://ranked-cvpr24.github.io.

翻译：图像边缘检测面临两大问题：（P1）正负类别间的高度不平衡，以及（P2）因不同标注者意见分歧导致的标签不确定性。现有方案通过类别平衡交叉熵损失和Dice损失解决P1，并通过仅预测多数标注者一致的边缘来应对P2。本文提出RankED——一种统一的基于排序的方法，同时处理不平衡问题（P1）与不确定性问题（P2）。RankED通过两个组件解决上述问题：一个组件对正像素与负像素进行排序，另一个组件促使高置信度边缘像素具有更高的标签确定性。实验表明，RankED优于先前研究，在NYUD-v2、BSDS500和Multi-cue数据集上达到新的最优水平。代码见https://ranked-cvpr24.github.io。