Abstract
Edge detection serves as a critical foundation for numerous computer vision applications, including object detection, semantic segmentation, and image editing, by extracting essential structural cues that define object boundaries and salient edges. To be viable for broad deployment across devices with varying computational capacities, edge detectors shall balance high accuracy with low computational complexity. While deep learning has evidently improved accuracy, they often suffer from high computational costs, limiting their applicability on resource-constrained devices. This paper addresses the challenge of achieving that balance: \textit{i.e.}, {how to efficiently capture discriminative features without relying on large-size and sophisticated models}. We propose PEdger++, a collaborative learning framework designed to reduce computational costs and model sizes while improving edge detection accuracy. The core principle of our PEdger++ is that cross-information derived from heterogeneous architectures, diverse training moments, and multiple parameter samplings, is beneficial to enhance learning from an ensemble perspective. Extensive experimental results on the BSDS500, NYUD and Multicue datasets demonstrate the effectiveness of our approach, both quantitatively and qualitatively, showing clear improvements over existing methods. We also provide multiple versions of the model with varying computational requirements, highlighting PEdger++'s adaptability with respect to different resource constraints. Codes are accessible at this https URL.
Abstract (translated)
边缘检测是众多计算机视觉应用的基础，包括物体检测、语义分割和图像编辑，它通过提取定义对象边界和显著边界的结构线索来发挥作用。为了在计算能力各异的设备上广泛部署，边缘检测器需要在高精度与低计算复杂度之间取得平衡。虽然深度学习明显提高了准确性，但由于其高昂的计算成本，限制了它们在资源受限设备上的应用。本文解决了这一挑战：即如何高效地捕捉鉴别特征而不依赖于大型且复杂的模型。我们提出了PEdger++，这是一个协作学习框架，旨在减少计算成本和模型尺寸的同时提高边缘检测精度。我们的PEdger++的核心理念是，来自异构架构、多样化训练时刻以及多个参数采样的交叉信息，在集合视角上对提升学习效果是有益的。 在BSDS500、NYUD和Multicue数据集上的大量实验结果表明了我们方法的有效性，无论是定量还是定性的评估都显示了相对于现有方法的明显改进。我们也提供了多种版本的模型，适应不同的计算需求，突显出PEdger++在面对不同资源约束时的灵活性。代码可以在提供的链接中获取。
URL
https://arxiv.org/abs/2508.11961
