以内点为中心的后训练量化方法用于目标检测模型
Inlier-Centric Post-Training Quantization for Object Detection Models
AI总结：
InlierQ通过梯度感知的体积显著性分数分离异常和信息性内点，实现目标检测模型的高效量化。
摘要：
目标检测在计算机视觉中至关重要，但其巨大的计算需求使得部署缓慢且耗电，推动了量化技术的发展。然而，任务无关的形态如背景杂波和传感器噪声会引发冗余激活（或异常）。这些异常扩大了激活范围，并使激活分布偏向于任务无关的响应，使位分配复杂化，并削弱了信息特征的保留。没有明确的标准来区分异常，抑制它们可能会无意中丢弃有用的信息。为此，我们提出了InlierQ，一种以内点为中心的后训练量化方法，用于分离异常和信息性内点。InlierQ计算梯度感知的体积显著性分数，将每个体积分类为内点或异常，并使用期望最大化（EM）算法拟合这些分数的后验分布。这种设计在抑制异常的同时保留了信息特征。InlierQ是无标签的、可直接替换的，并且仅需要64个校准样本。在COCO和nuScenes基准测试中，InlierQ在基于相机（2D和3D）和基于LiDAR（3D）的目标检测中显示出一致的量化误差减少。
英文摘要：
Object detection is pivotal in computer vision, yet its immense computational demands make deployment slow and power-hungry, motivating quantization. However, task-irrelevant morphologies such as background clutter and sensor noise induce redundant activations (or anomalies). These anomalies expand activation ranges and skew activation distributions toward task-irrelevant responses, complicating bit allocation and weakening the preservation of informative features. Without a clear criterion to distinguish anomalies, suppressing them can inadvertently discard useful information. To address this, we present InlierQ, an inlier-centric post-training quantization approach that separates anomalies from informative inliers. InlierQ computes gradient-aware volume saliency scores, classifies each volume as an inlier or anomaly, and fits a posterior distribution over these scores using the Expectation-Maximization (EM) algorithm. This design suppresses anomalies while preserving informative features. InlierQ is label-free, drop-in, and requires only 64 calibration samples. Experiments on the COCO and nuScenes benchmarks show consistent reductions in quantization error for camera-based (2D and 3D) and LiDAR-based (3D) object detection.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
