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

2025-11-16

AI Summary

To address the limitation of uniform quantization accuracy caused by heterogeneous spatial complexity in visual data, this paper proposes a morphology-aware adaptive quantization framework. We introduce five morphological metrics—fractal dimension, texture entropy, gradient variance, edge density, and contour complexity—to quantify local structural complexity, and integrate them with a curriculum learning strategy to enable dynamic bit-width allocation and progressive quantization training. Evaluated on a safety equipment detection task, our method achieves 85.6% mAP@0.5 at an average bit-width of 4.2 bits—outperforming uniform 4-bit quantization by 3.5 percentage points—while attaining a 7.6× model compression ratio. Inference latency increases by only 1.8 ms per image. The framework significantly enhances quantization accuracy, computational efficiency, and robustness without compromising practical deployability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Most neural network quantization methods apply uniform bit precision across spatial regions, ignoring the heterogeneous structural and textural complexity of visual data. This paper introduces MCAQ-YOLO, a morphological complexity-aware quantization framework for object detection. The framework employs five morphological metrics - fractal dimension, texture entropy, gradient variance, edge density, and contour complexity - to characterize local visual morphology and guide spatially adaptive bit allocation. By correlating these metrics with quantization sensitivity, MCAQ-YOLO dynamically adjusts bit precision according to spatial complexity. In addition, a curriculum-based quantization-aware training scheme progressively increases quantization difficulty to stabilize optimization and accelerate convergence. Experimental results demonstrate a strong correlation between morphological complexity and quantization sensitivity and show that MCAQ-YOLO achieves superior detection accuracy and convergence efficiency compared with uniform quantization. On a safety equipment dataset, MCAQ-YOLO attains 85.6 percent mAP@0.5 with an average of 4.2 bits and a 7.6x compression ratio, yielding 3.5 percentage points higher mAP than uniform 4-bit quantization while introducing only 1.8 ms of additional runtime overhead per image. Cross-dataset validation on COCO and Pascal VOC further confirms consistent performance gains, indicating that morphology-driven spatial quantization can enhance efficiency and robustness for computationally constrained, safety-critical visual recognition tasks.

Problem

• Uniform quantization ignores varying visual complexity across spatial regions
• Existing methods lack spatial adaptation to morphological data characteristics
• Quantization sensitivity requires correlation with local structural complexity metrics

Innovation

• Uses morphological metrics to guide adaptive bit allocation
• Employs curriculum learning to progressively increase quantization difficulty
• Dynamically adjusts bit precision based on spatial complexity