Abstract
Learning-based edge detection models trained with cross-entropy loss often suffer from thick edge predictions, which deviate from the crisp, single-pixel annotations typically provided by humans. While previous approaches to achieving crisp edges have focused on designing specialized loss functions or modifying network architectures, we show that a carefully designed training and inference strategy alone is sufficient to achieve human-like edge quality. In this work, we introduce the Masked Edge Prediction MOdel (MEMO), which produces both accurate and crisp edges using only cross-entropy loss. We first construct a large-scale synthetic edge dataset to pre-train MEMO, enhancing its generalization ability. Subsequent fine-tuning on downstream datasets requires only a lightweight module comprising 1.2\% additional parameters. During training, MEMO learns to predict edges under varying ratios of input masking. A key insight guiding our inference is that thick edge predictions typically exhibit a confidence gradient: high in the center and lower toward the boundaries. Leveraging this, we propose a novel progressive prediction strategy that sequentially finalizes edge predictions in order of prediction confidence, resulting in thinner and more precise contours. Our method achieves visually appealing, post-processing-free, human-like edge maps and outperforms prior methods on crispness-aware evaluations.
Abstract (translated)
基于交叉熵损失实现精准锐利的边缘检测，一直是计算机视觉领域的一项挑战。本文提出了MEMO模型，仅通过交叉熵损失即可生成既准确又锐利的边缘。我们首先构建了一个大规模合成边缘数据集用于预训练MEMO，以增强其泛化能力。随后在各类下游数据集上的微调仅需一个轻量级模块，该模块仅增加1.2%的参数。在训练过程中，MEMO学习在不同比例的输入掩码下预测边缘。其推理过程的核心思想是：粗边缘预测通常呈现置信度梯度——中心区域置信度高，向边缘边界逐渐降低。基于此，我们提出一种新颖的渐进式预测策略，该策略按预测置信度顺序逐步确定边缘，从而得到更细、更精确的轮廓。我们的方法能够生成无需后处理、视觉上媲美人工标注的优美边缘图，并在锐利度感知的评估指标上超越了以往方法。
URL
https://arxiv.org/abs/2603.20782
