发表机构
Hangzhou City University; Zhejiang University; ICREA; TU Wien（杭州城市大学; 浙江大学; 加泰罗尼亚研究与高级研究所; 维也纳技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LipCache是带可验证缓存的边缘图像分类本地推理代理，通过轻量GuardNet实现几何可验证缓存决策，在多数据集上获最高1.65倍加速，且保持可验证一致性，为边缘缓存辅助推理提供可行方案。
AI 中文摘要
随着边缘侧视觉服务不断向低延迟、高吞吐量场景扩展，在不牺牲可靠性的前提下降低视觉模型的推理成本已成为核心关注点。现有的语义缓存方法大多依赖经验相似度阈值，这类阈值虽能提升命中率，但往往会在决策边界附近引入隐性误分类。为解决该问题，我们提出LipCache，这是一种面向图像分类的可验证语义缓存框架。该框架无需修改已部署的主模型MainNet，仅引入轻量网络GuardNet，将输入映射到满足Lipschitz约束的低维特征空间；随后基于局部分类间隔与分类头的谱范数计算每个样本的可验证重用半径。运行时仅当查询特征落在可验证重用球内时才复用缓存结果，否则回退至MainNet。由此，缓存命中从经验阈值测试转变为具有明确理论边界的几何可验证决策。在CIFAR、Tiny-ImageNet、SVHN等标准图像分类任务中，LipCache实现了最高1.65倍的实测加速，端到端准确率下降有限，且所有被接受的缓存命中均满足GuardNet侧的可验证一致性条件。此外，改进的GuardNet训练方案在保持100%可验证一致性率的同时，大幅提升了Tiny-ImageNet多分类扩展任务的缓存命中率。这些结果表明，基于样本的可验证重用可减少主模型回退，同时保持理论一致性，为边缘场景下可靠的缓存辅助推理提供了可行方案。
英文摘要
As edge-side vision services continue to expand toward low-latency, high-throughput scenarios, reducing the inference cost of vision models without sacrificing reliability has become a central concern. Existing semantic caching methods largely rely on empirical similarity thresholds; while such thresholds improve hit rates, they tend to introduce silent misclassifications near decision boundaries. To address this, we propose \texttt{LipCache}, a certified semantic caching framework for image classification. Without modifying the existing deployed main model, \texttt{MainNet}, the framework introduces a lightweight network, \texttt{GuardNet}, that maps inputs into a low-dimensional feature space subject to a Lipschitz constraint. It then computes a per-sample certified reuse radius from the local classification margin and the spectral norm of the classification head. At runtime, a cached result is reused only when the query feature falls inside the certified reuse ball; otherwise, the query falls back to \texttt{MainNet}. Thus, cache hits are transformed from empirical threshold tests into geometric certification decisions with explicit theoretical boundaries. Across standard image classification tasks like CIFAR, Tiny-ImageNet, and SVHN, \texttt{LipCache} achieves a measured speedup of up to $1.65\times$ with limited end-to-end accuracy degradation, while all accepted cache hits satisfy the \texttt{GuardNet}-side certified-consistency condition. Furthermore, an enhanced \texttt{GuardNet} training recipe substantially improves cache hit rates in the Tiny-ImageNet multi-class extension while maintaining a certified-consistency rate of $100\%$. These results demonstrate that per-sample certified reuse can reduce main-model fallback while preserving theoretical consistency, providing a feasible approach to reliable cache-assisted inference at the edge.
