MCAQ-YOLO: Morphological Complexity-Aware Quantization for Efficient Object Detection with Curriculum Learning

TL;DR

MCAQ-YOLO introduces a morphology-aware mixed-precision quantization framework with curriculum learning for efficient, high-accuracy real-time object detection, adapting bit precision based on spatial complexity.

Contribution

It proposes a novel complexity metric-based spatial quantization method combined with curriculum training, enabling efficient, adaptive neural network quantization for object detection.

Findings

Achieves 85.6% mAP@0.5 with 4.2-bit average precision and 7.6x compression.

Outperforms uniform 4-bit quantization by 3.5 percentage points.

Demonstrates consistent improvements across multiple datasets.

Abstract

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% mAP@0.5 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.