LIMODENet：用于信息保持的星载卫星图像复原的无注意力紧凑编码器
LIMODENet: Attention-Free Compact Encoders for Information-Preserving Onboard Satellite Image Restoration
浏览论文内容
中文总结 AI 辅助
针对神经形态硬件不支持注意力的约束，提出无注意力紧凑编码器LIMODENet，以0.69M参数实现信息保持的星载图像复原，优于CNN和U-Net，并端到端转换为零阻塞脉冲网络。
中文摘要 AI 辅助
星载卫星必须在几瓦的功耗预算内，使用不支持softmax或注意力的神经形态加速器（如BrainChip Akida、Intel Loihi-2）恢复信道退化的图像。我们探究在此约束下哪种编码器恢复效果最佳，并引入LIMODENet（LinearMix-ODENet），这是一个0.69M参数、无softmax/QKV的骨干网络，其残差阶段可视为ODE离散化，并且经验上保持信息（探针准确率从stem到head从79.9%提升至98.4%）。在等参数条件下，它恢复1 dB DVB-S2X退化EuroSAT图像的效果优于CNN自编码器（+1.75 dB PSNR）和带跳跃连接的U-Net（+1.07 dB），使用三个随机种子且不重叠。无约束的现代复原器（NAFNet、Restormer）在保真度上胜出；我们分解了这一差距：脉冲合法的加法跳跃恢复约一半，其余归因于注意力和通道门控。LIMODENet随后端到端转换为脉冲网络，零阻塞操作，而竞争对手有22-24个阻塞操作：它不是可用的最佳复原器，但是在实际功耗预算内经过验证的最佳可部署方案。
英文摘要
Onboard satellites must restore a channel-degraded image on a few watts, using neuromorphic accelerators (e.g., BrainChip Akida, Intel Loihi-2) that support no softmax or attention. We ask which encoder restores best under that constraint and introduce LIMODENet (LinearMix-ODENet), a 0.69M softmax-/QKV-free backbone whose residual stages read as ODE discretizations and which is empirically information-preserving (probe accuracy rises 79.9% -> 98.4% from stem to head). At iso-parameters it restores 1 dB DVB-S2X-degraded EuroSAT better than a CNN autoencoder (+1.75 dB PSNR) and a skip-connection U-Net (+1.07 dB), three seeds, non-overlapping. Unconstrained modern restorers (NAFNet, Restormer) win on fidelity; we decompose that gap: spiking-legal additive skips recover about half, and the rest traces to attention and channel gating. LIMODENet then converts end-to-end to a spiking network with zero blocked operations, versus 22-24 for the competitors: not the best restorer available, but the best verified deployable within a real power budget.
发表机构
- Texas A&M University - Corpus Christi（德克萨斯A&M大学科珀斯克里斯蒂分校）
- University of Luxembourg（卢森堡大学）
机构由 AI 辅助整理，请以论文原文为准。
