效率源于全局-局部解耦
Efficiency Follows Global-Local Decoupling
把全局上下文聚合与局部特征提取拆成两条分支、用轻量 token 上的神经记忆做全局推理，可作为一种即插即用的骨干设计，在分类/检测/分割中替代全全局注意力以换取更优的精度-延迟权衡。
原文依据 a lightweight neural memory branch aggregates global context on a compact set of tokens
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现代视觉模型必须在保持计算可负担的同时，既捕获图像级上下文又不牺牲局部细节。我们重新审视这一权衡，并提出一条简单的原则：解耦全局推理与局部表征各自的角色。为落实这一原则，我们提出 ConvNeur，一种双分支架构，其中轻量的神经记忆分支在一组紧凑的 token 上聚合全局上下文，而保局部性的分支负责提取精细结构。一个可学习的门控让全局线索调制局部特征，同时不使二者的目标相互纠缠。这种分离带来了随图像尺寸的次二次方扩展、保留了与局部处理相关的归纳先验，并相对全全局注意力降低了开销。在标准分类、检测与分割基准上，ConvNeur 在相近或更低计算量下达到或超过可比方案，并在相近预算下提供更优的精度与延迟权衡。这些结果支持如下观点：效率源于全局-局部解耦。
英文原文摘要 1067 字符
Modern vision models must capture image-level context without sacrificing local detail while remaining computationally affordable. We revisit this tradeoff and advance a simple principle: decouple the roles of global reasoning and local representation. To operationalize this principle, we introduce ConvNeur, a two-branch architecture in which a lightweight neural memory branch aggregates global context on a compact set of tokens, and a locality-preserving branch extracts fine structure. A learned gate lets global cues modulate local features without entangling their objectives. This separation yields subquadratic scaling with image size, retains inductive priors associated with local processing, and reduces overhead relative to fully global attention. On standard classification, detection, and segmentation benchmarks, ConvNeur matches or surpasses comparable alternatives at similar or lower compute and offers favorable accuracy versus latency trade-offs at similar budgets. These results support the view that efficiency follows global-local decoupling.