在CNN语义分割中，用稀疏专家层提升模型能力，性能提升3.9 mIoU且开销极小。
Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
- 将稀疏专家层按图像块粗粒度路由，替代传统CNN的全连接模块。
- 在Cityscapes和BDD100K上实现最高+3.9 mIoU增益，计算开销几乎不变。
- 揭示了专家路由与架构设计间的敏感关系，适合关注模型效率的开发者。
稀疏混合专家（MoE）层可显著提升模型容量而无需成比例增加计算成本，已在Transformer架构中广泛应用，通常替换前馈网络模块。相比之下，将稀疏MoE层融入卷积神经网络（CNN）仍不一致，多数先前工作聚焦于滤波器或通道级别的细粒度MoE。本文研究了一种面向语义分割的粗粒度、块级稀疏MoE层设计，其中局部区域被路由至少量卷积专家。基于编码器-解码器和主干网络，在Cityscapes和BDD100K数据集上进行实验，分析架构选择对路由动态与专家专属性的影响。结果表明，模型在不同架构下均实现稳定提升（最高+3.9 mIoU），且计算开销极低，同时揭示了强烈的设计敏感性。本工作为基于CNN的密集预测任务中稀疏MoE层的设计与内部机制提供了实证洞察。代码已开源：https://github.com/KASTEL-MobilityLab/moe-layers/
原文摘要 · Abstract (English)
Sparse mixture-of-experts (MoE) layers have been shown to substantially increase model capacity without a proportional increase in computational cost and are widely used in transformer architectures, where they typically replace feed-forward network blocks. In contrast, integrating sparse MoE layers into convolutional neural networks (CNNs) remains inconsistent, with most prior work focusing on fine-grained MoEs operating at the filter or channel levels. In this work, we investigate a coarser, patch-wise formulation of sparse MoE layers for semantic segmentation, where local regions are routed to a small subset of convolutional experts. Through experiments on the Cityscapes and BDD100K datasets using encoder-decoder and backbone-based CNNs, we conduct a design analysis to assess how architectural choices affect routing dynamics and expert specialization. Our results demonstrate consistent, architecture-dependent improvements (up to +3.9 mIoU) with little computational overhead, while revealing strong design sensitivity. Our work provides empirical insights into the design and internal dynamics of sparse MoE layers in CNN-based dense prediction. Our code is available at https://github.com/KASTEL-MobilityLab/moe-layers/.
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。