用1D卷积替代2D卷积，让分割模型更轻量适合边缘设备
OneNet: A Channel-Wise 1D Convolutional U-Net
- 用通道级1D卷积+PixelUnshuffle替代传统2D卷积
- 参数减少47%，在分割任务中保持接近U-Net的精度
- 特别适合资源受限的边缘部署，代码已开源
许多先进的计算机视觉架构采用U-Net，因其适应性强且特征提取高效。然而，多分辨率卷积设计常带来巨大计算负担，限制了在边缘设备上的部署。本文提出一种简化方案：基于1D卷积的编码器，在保持精度的同时提升边缘适用性。新架构通过通道级1D卷积与PixelUnshuffle操作实现语义分割，避免使用2D卷积，从而将参数量最多降低47%。此外，我们还探索了全1D编码器-解码器结构，尺寸减少71%，尽管精度略有下降。我们在多种掩码生成任务上对比了U-Net变体，结果表明该方法能有效保留精度。虽聚焦于图像分割，但该架构可推广至其他卷积应用。项目代码已公开于https://github.com/shbyun080/OneNet。
原文摘要 · Abstract (English)
Many state-of-the-art computer vision architectures leverage U-Net for its adaptability and efficient feature extraction. However, the multi-resolution convolutional design often leads to significant computational demands, limiting deployment on edge devices. We present a streamlined alternative: a 1D convolutional encoder that retains accuracy while enhancing its suitability for edge applications. Our novel encoder architecture achieves semantic segmentation through channel-wise 1D convolutions combined with pixel-unshuffle operations. By incorporating PixelShuffle, known for improving accuracy in super-resolution tasks while reducing computational load, OneNet captures spatial relationships without requiring 2D convolutions, reducing parameters by up to 47%. Additionally, we explore a fully 1D encoder-decoder that achieves a 71% reduction in size, albeit with some accuracy loss. We benchmark our approach against U-Net variants across diverse mask-generation tasks, demonstrating that it preserves accuracy effectively. Although focused on image segmentation, this architecture is adaptable to other convolutional applications. Code for the project is available at https://github.com/shbyun080/OneNet .
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。