Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detection
作者: Hao Shu
分类: cs.CV, cs.AI
发布日期: 2025-01-23 (更新: 2026-01-15)
备注: 39 pages
💡 一句话要点
提出SWBCE损失函数以解决边缘检测中的感知不对称问题
🎯 匹配领域: 支柱三:空间感知与语义 (Perception & Semantics)
关键词: 边缘检测 深度学习 损失函数 计算机视觉 感知一致性 模型优化 神经网络
📋 核心要点
- 现有边缘检测模型虽然在数值准确性上取得了进展,但在视觉质量和感知一致性上仍存在不足。
- 本文提出的SWBCE损失函数通过引入感知不对称性,优化边缘检测模型的学习过程,提升边缘回忆率并抑制假阳性。
- 实验结果显示,SWBCE在多个数据集上均表现优异,尤其在HED-EES模型中,SSIM提升显著,展现了其在感知结果上的优势。
📝 摘要(中文)
边缘检测是计算机视觉中的基本感知过程,为高层推理任务如分割、识别和场景理解奠定了结构基础。尽管深度神经网络在边缘检测方面取得了显著进展,但大多数模型在视觉上未能产生清晰且感知一致的边缘,限制了其在智能视觉系统中的可靠性。为了解决这一问题,本文提出了感知启发的对称加权二元交叉熵损失函数(SWBCE),通过引入预测引导的对称性,扩展了传统的加权二元交叉熵。SWBCE明确建模了人类边缘识别中的感知不对称性,使得边缘决策需要比非边缘决策更强的证据,从而使优化过程与人类的感知区分相一致。实验表明,SWBCE在多个基准数据集和代表性边缘检测架构中均优于现有损失函数,尤其是在HED-EES模型上,SSIM在BRIND数据集上提高了约15%。
🔬 方法详解
问题定义:本文旨在解决现有边缘检测模型在视觉质量和感知一致性上的不足,尤其是模型在产生清晰边缘方面的挑战。
核心思路:提出SWBCE损失函数,通过建模人类边缘识别中的感知不对称性,使得边缘决策需要更强的证据,从而优化模型的学习过程。
技术框架:SWBCE损失函数在传统加权二元交叉熵的基础上,加入了预测引导的对称性,形成了一种新的学习机制,增强了边缘检测的性能。
关键创新:SWBCE的最大创新在于其感知启发的设计,明确区分边缘与非边缘的证据强度,提升了模型在边缘检测任务中的感知一致性。
关键设计:SWBCE损失函数的设计考虑了边缘和非边缘的证据强度差异,优化了损失函数的参数设置,使得模型在训练过程中能够更好地学习到边缘特征。
🖼️ 关键图片
📊 实验亮点
实验结果表明,SWBCE在多个基准数据集上均优于现有损失函数,尤其在HED-EES模型中,SSIM在BRIND数据集上提升了约15%,显示出其在视觉质量上的显著改善。
🎯 应用场景
该研究的SWBCE损失函数不仅适用于边缘检测,还为软计算和神经学习系统提供了一种可推广的优化原则,特别是在需要处理不对称感知推理的场景中,具有广泛的应用潜力和实际价值。
📄 摘要(原文)
Edge detection (ED) is a fundamental perceptual process in computer vision, forming the structural basis for high-level reasoning tasks such as segmentation, recognition, and scene understanding. Despite substantial progress achieved by deep neural networks, most ED models attain high numerical accuracy but fail to produce visually sharp and perceptually consistent edges, thereby limiting their reliability in intelligent vision systems. To address this issue, this study introduces the \textit{Symmetrization Weighted Binary Cross-Entropy (SWBCE)} loss, a perception-inspired formulation that extends the conventional WBCE by incorporating prediction-guided symmetry. SWBCE explicitly models the perceptual asymmetry in human edge recognition, wherein edge decisions require stronger evidence than non-edge ones, aligning the optimization process with human perceptual discrimination. The resulting symmetric learning mechanism jointly enhances edge recall and suppresses false positives, achieving a superior balance between quantitative accuracy and perceptual fidelity. Extensive experiments across multiple benchmark datasets and representative ED architectures demonstrate that SWBCE can outperform existing loss functions in both numerical evaluation and visual quality. Particularly with the HED-EES model, the SSIM can be improved by about 15% on BRIND, and in all experiments, training by SWBCE consistently obtains the best perceptual results. Beyond edge detection, the proposed perceptual loss offers a generalizable optimization principle for soft computing and neural learning systems, particularly in scenarios where asymmetric perceptual reasoning plays a critical role.