Recti-Q：用于边缘机器人中分布外鲁棒量化感知的特征空间校正
Recti-Q: Feature-Space Rectification for Out-of-Distribution-Robust Quantized Perception in Edge Robotics
浏览论文内容
中文总结 AI 辅助
研究针对边缘机器人中PTQ在分布变化下可靠性降低的问题，提出轻量级特征空间校正框架Recti-Q，它冻结量化主干，仅用源数据训练小型分类器头LoRA适配器，与架构无关，能恢复鲁棒性，节省内存且实现低带宽OTA弹性修补。
中文摘要 AI 辅助
机器人感知管道越来越依赖于部署在受SWaP约束的边缘平台上的大型视觉主干，使得训练后量化（PTQ）对实时推理具有吸引力。然而，虽然PTQ通常能保持干净的分布内精度，但在与部署相关的分布变化（如传感器噪声、恶劣天气和新的操作环境）下，它可能会大幅降低可靠性，造成量化诱导的鲁棒性差距。在基础视觉基准测试中，4位PTQ模型尽管分布内精度损失可忽略不计，但鲁棒性却显著下降。为解决此问题，我们提出了Recti-Q，这是一个轻量级特征空间校正框架，它冻结量化主干，并仅使用源数据训练一个小型分类器头LoRA适配器。Recti-Q在CNN和Transformer中与架构无关，支持高效的无教师训练，并恢复了大部分损失的鲁棒性，在某些情况下达到或超过了FP32性能。在参数开销小于1%（小至6KB）的情况下，Recti-Q保留了超过99%的PTQ内存节省，增加的计算可忽略不计，并为在不可预测物理环境中运行的已部署机器人机队实现了低带宽空中（OTA）弹性修补。
英文摘要
Robotic perception pipelines increasingly rely on large vision backbones deployed on SWaP-constrained edge platforms, making post-training quantization (PTQ) attractive for real-time inference. However, while PTQ often preserves clean in-distribution accuracy, we show that it can substantially degrade reliability under deployment-relevant distribution shifts (e.g., sensor noise, severe weather, and novel operating environments), creating a Quantization-Induced Robustness Gap. Across foundational vision benchmarks (ImageNet-C and PACS), 4-bit PTQ models exhibit pronounced robustness degradation despite negligible ID accuracy loss. To address this, we propose Recti-Q, a lightweight feature-space rectification framework that freezes the quantized backbone and trains a small classifier-head LoRA adapter using only source data. Recti-Q is architecture-agnostic across CNNs and Transformers, supports efficient teacher-free training, and recovers a significant portion of the lost robustness, in some cases matching or exceeding FP32 performance. At less than 1% parameter overhead (as small as 6 KB), Recti-Q preserves over 99% of PTQ memory savings, adds negligible compute, and enables low-bandwidth Over-The-Air (OTA) resilience patching for deployed robotic fleets operating in unpredictable physical environments.
