基于边缘检测的初始化方法，显著减少SMoE模型优化开销。
Edge-Aligned Initialization of Kernels for Steered Mixture-of-Experts
- 用Canny边缘检测提取图像轮廓，确定专家核的位置与方向
- 无需随机优化即可实现高质量图像重建
- 适合需要快速部署的图像处理任务
导向式混合专家（Steered Mixture-of-Experts, SMoE）最近成为一种强大的空间域图像建模框架，仅用少量参数即可实现高保真图像表示。其通过引导基于核的专家对齐图像结构特征，在图像压缩、去噪、超分辨率和光场处理中取得成功应用。然而，实际应用受限于依赖梯度优化在每幅图像上估计参数——该过程计算量大且难以扩展。SMoE的初始化策略直接影响收敛速度与重建质量。本文提出一种新型边缘驱动的初始化方案，通过Canny边缘检测提取稀疏图像轮廓，确定核位置与方向，并独立估计初始专家系数，实现定性推断。该方法显著降低内存消耗与计算成本，同时保持良好重建质量。
原文摘要 · Abstract (English)
Steered Mixture-of-Experts (SMoE) has recently emerged as a powerful framework for spatial-domain image modeling, enabling high-fidelity image representation using a remarkably small number of parameters. Its ability to steer kernel-based experts toward structural image features has led to successful applications in image compression, denoising, super-resolution, and light field processing. However, practical adoption is hindered by the reliance on gradient-based optimization to estimate model parameters on a per-image basis - a process that is computationally intensive and difficult to scale. Initialization strategies for SMoE are an essential component that directly affects convergence and reconstruction quality. In this paper, we propose a novel, edge-based initialization scheme that achieves good reconstruction qualities while reducing the need for stochastic optimization significantly. Through a method that leverages Canny edge detection to extract a sparse set of image contours, kernel positions and orientations are deterministically inferred. A separate approach enables the direct estimation of initial expert coefficients. This initialization reduces both memory consumption and computational cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。