Edge detection is a fundamental image analysis task that underpins numerous high-level vision applications. Recent advances in Transformer architectures have significantly improved edge quality by capturing long-range dependencies, but this often comes with computational overhead. Achieving higher pixel-level accuracy requires increased input resolution, further escalating computational cost and limiting practical deployment. Building on the strong representational capacity of recent Transformer-based edge detectors, we propose an Adaptive Multi-stage non-edge Pruning framework for Edge Detection(Amped). Amped identifies high-confidence non-edge tokens and removes them as early as possible to substantially reduce computation, thus retaining high accuracy while cutting GFLOPs and accelerating inference with minimal performance loss. Moreover, to mitigate the structural complexity of existing edge detection networks and facilitate their integration into real-world systems, we introduce a simple yet high-performance Transformer-based model, termed Streamline Edge Detector(SED). Applied to both existing detectors and our SED, the proposed pruning strategy provides a favorable balance between accuracy and efficiency-reducing GFLOPs by up to 40% with only a 0.4% drop in ODS F-measure. In addition, despite its simplicity, SED achieves a state-of-the-art ODS F-measure of 86.5%. The code will be released.

翻译：摘要：边缘检测是一项基础的图像分析任务，支撑着众多高层视觉应用。Transformer架构的最新进展通过捕获长距离依赖显著提升了边缘质量，但这通常伴随着计算开销的增加。要实现更高的像素级精度，需要提升输入分辨率，这进一步加剧了计算成本并限制了实际部署。基于近期基于Transformer的边缘检测器的强大表征能力，我们提出了一种面向边缘检测的自适应多阶段非边缘剪枝框架（Amped）。Amped能够识别高置信度的非边缘标记，并尽早移除它们以大幅降低计算量，从而在保持高精度的同时减少GFLOPs并加速推理，且性能损失极小。此外，为降低现有边缘检测网络的结构复杂度并促进其在实际系统中的集成，我们引入了一种简洁而高性能的基于Transformer的模型，称为流线型边缘检测器（SED）。将该剪枝策略应用于现有检测器及我们的SED，可在精度与效率之间取得良好平衡——GFLOPs最高减少40%，而ODS F值仅下降0.4%。同时，尽管SED设计简洁，其ODS F值仍达到86.5%的先进水平。相关代码将予以公开。