Abstract
Vision modeling has advanced rapidly with Transformers, whose attention mechanisms capture visual dependencies but lack a principled account of how semantic information propagates spatially. We revisit this problem from a wave-based perspective: feature maps are treated as spatial signals whose evolution over an internal propagation time (aligned with network depth) is governed by an underdamped wave equation. In this formulation, spatial frequency-from low-frequency global layout to high-frequency edges and textures-is modeled explicitly, and its interaction with propagation time is controlled rather than implicitly fixed. We derive a closed-form, frequency-time decoupled solution and implement it as the Wave Propagation Operator (WPO), a lightweight module that models global interactions in O(N log N) time-far lower than attention. Building on WPO, we propose a family of WaveFormer models as drop-in replacements for standard ViTs and CNNs, achieving competitive accuracy across image classification, object detection, and semantic segmentation, while delivering up to 1.6x higher throughput and 30% fewer FLOPs than attention-based alternatives. Furthermore, our results demonstrate that wave propagation introduces a complementary modeling bias to heat-based methods, effectively capturing both global coherence and high-frequency details essential for rich visual semantics. Codes are available at: this https URL.
Abstract (translated)
视觉模型在Transformer架构的推动下取得了快速进展，但其注意机制虽能捕捉视觉依赖关系，却缺乏对语义信息如何在空间上传播的原理性解释。我们从波的观点重新审视这个问题：将特征图视为空间信号，并将其随内部传播时间（与网络深度相一致）演化的规律用一个欠阻尼波动方程来描述。在这种框架下，空间频率——从低频全局布局到高频边缘和纹理——被明确建模，且其与传播时间的相互作用不再是隐式固定的，而是可以控制的。 我们推导出了一种闭合形式、频率-时间解耦的解决方案，并将其实现为波传播算子（WPO），这是一种轻量级模块，在O(N log N)时间内模型全局交互，远低于注意力机制。基于WPO，我们提出了一系列WaveFormer模型作为标准ViTs和CNNs的直接替代品，在图像分类、目标检测和语义分割等任务上达到了竞争性的准确率，并且相比基于注意的方法提供了最高达1.6倍的吞吐量和30%更少的FLOPs。此外，我们的结果表明波传播为热基方法引入了一种互补建模偏差，有效捕捉了全局一致性及高频细节，这对丰富视觉语义至关重要。 代码可在以下网址获取：[请参考原文链接以查看准确URL]
URL
https://arxiv.org/abs/2601.08602
