Image Edge detection (ED) is a base task in computer vision. While the performance of the ED algorithm has been improved greatly by introducing CNN-based models, current models still suffer from unsatisfactory precision rates especially when only a low error toleration distance is allowed. Therefore, model architecture for more precise predictions still needs an investigation. On the other hand, the unavoidable noise training data provided by humans would lead to unsatisfactory model predictions even when inputs are edge maps themselves, which also needs a solution. In this paper, more precise ED models are presented with cascaded skipping density blocks (CSDB). Our models obtain state-of-the-art(SOTA) predictions in several datasets, especially in average precision rate (AP), over a high-standard benchmark, which is confirmed by extensive experiments. Also, a novel modification on data augmentation for training is employed, which allows noiseless data to be employed in model training for the first time, and thus further improves the model performance. The relative Python codes can be found on https://github.com/Hao-B-Shu/SDPED.

翻译：图像边缘检测是计算机视觉中的基础任务。尽管通过引入基于CNN的模型，边缘检测算法的性能已得到显著提升，但现有模型在仅允许较小误差容忍距离时仍存在精度不足的问题。因此，仍需研究能够实现更精确预测的模型架构。另一方面，人工标注训练数据中不可避免的噪声会导致模型预测效果不佳——即使输入为边缘图本身时亦然，此问题亦需解决。本文提出采用级联跳跃密度块的更精确边缘检测模型。我们的模型在多个数据集上取得了最先进的预测性能，特别是在平均精度指标上超越了高标准基准，这已通过大量实验验证。此外，我们采用了一种新颖的训练数据增强改进方法，首次实现了在模型训练中使用无噪声数据，从而进一步提升了模型性能。相关Python代码可在https://github.com/Hao-B-Shu/SDPED获取。