根据图像复杂度动态分配精度，提升目标检测效率与准确率
MCAQ-YOLO: Morphological Complexity-Aware Quantization for Efficient Object Detection with Curriculum Learning
- 按图像区域复杂度分配不同位宽，避免统一量化损失
- 实测达85.6% [email protected]，压缩7.6倍，比固定4比特高3.5个百分点
- 适合高复杂度场景如工地安全检测，且可快速部署
现有神经网络量化方法对空间区域采用统一位宽，忽视视觉数据的异质性。本文提出MCAQ-YOLO，一种面向实时目标检测器的像素块级混合精度量化框架。通过五种互补指标（分形维数、纹理熵、梯度方差、边缘密度、轮廓复杂度）量化形态复杂度，作为空间量化敏感性的信号中心预测因子。校准阶段仅增加0.3ms推理开销，实现151 FPS吞吐量。引入基于课程学习的训练策略，逐步增加量化难度以稳定优化并加速收敛。在具有高度形态变异性的施工安全设备数据集上，MCAQ-YOLO实现85.6% [email protected]，平均位宽4.2比特，压缩比达7.6倍，优于均匀4比特量化3.5个百分点。跨数据集评估在COCO 2017（+2.9%）和Pascal VOC 2012（+2.3%）上均表现一致提升，性能增益与图像内复杂度变化相关。
原文摘要 · Abstract (English)
Most neural network quantization methods apply uniform bit precision across spatial regions, disregarding the heterogeneous complexity inherent in visual data. This paper introduces MCAQ-YOLO, a practical framework for tile-wise spatial mixed-precision quantization in real-time object detectors. Morphological complexity--quantified through five complementary metrics (fractal dimension, texture entropy, gradient variance, edge density, and contour complexity)--is proposed as a signal-centric predictor of spatial quantization sensitivity. A calibration-time analysis design enables spatial bit allocation with only 0.3ms inference overhead, achieving 151 FPS throughput. Additionally, a curriculum-based training scheme that progressively increases quantization difficulty is introduced to stabilize optimization and accelerate convergence. On a construction safety equipment dataset exhibiting high morphological variability, MCAQ-YOLO achieves 85.6% [email protected] with an average bit-width of 4.2 bits and a 7.6x compression ratio, outperforming uniform 4-bit quantization by 3.5 percentage points. Cross-dataset evaluation on COCO 2017 (+2.9%) and Pascal VOC 2012 (+2.3%) demonstrates consistent improvements, with performance gains correlating with within-image complexity variation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。