用可学习的加法连接替代拼接，让去噪模型更轻量且可解释。
Rethinking Skip Connections: Additive U-Net for Robust and Interpretable Denoising
- 用可学习的标量缩放跳连，实现可控的信息传递。
- 在σ=15/25/50噪声下，性能媲美传统U-Net，且对网络深度和调度鲁棒。
- 无需强制分层或上下采样，自然学到多尺度特征演化过程。
跳连是图像去噪U-Net架构的核心，但标准拼接会加倍通道数并模糊信息流，导致噪声不受控传播。本文提出加法U-Net，以门控加法连接替代拼接。每个跳连路径由可学习的非负标量缩放，实现对编码器贡献的显式、可解释控制，避免通道膨胀。在Kodak-17去噪基准上，加法U-Net在噪声水平σ=15、25、50下均取得竞争力的PSNR/SSIM，且对核调度和网络深度具有鲁棒性。值得注意的是，即使无显式上下采样或强制层次结构，模型仍能自然学习从高频到带通再到低频特征的演化过程。结果表明，加法跳连是拼接的轻量级、可解释替代方案，有助于高效设计与理解重建网络中的多尺度信息传递。
原文摘要 · Abstract (English)
Skip connections are central to U-Net architectures for image denoising, but standard concatenation doubles channel dimensionality and obscures information flow, allowing uncontrolled noise transfer. We propose the Additive U-Net, which replaces concatenative skips with gated additive connections. Each skip pathway is scaled by a learnable non-negative scalar, offering explicit and interpretable control over encoder contributions while avoiding channel inflation. Evaluations on the Kodak-17 denoising benchmark show that Additive U-Net achieves competitive PSNR/SSIM at noise levels σ = 15, 25, 50, with robustness across kernel schedules and depths. Notably, effective denoising is achieved even without explicit down/up-sampling or forced hierarchies, as the model naturally learns a progression from high-frequency to band-pass to low-frequency features. These results position additive skips as a lightweight and interpretable alternative to concatenation, enabling both efficient design and a clearer understanding of multi-scale information transfer in reconstruction networks.
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。