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

• URL: http://arxiv.org/abs/2511.12976v1
• Date: Mon, 17 Nov 2025 04:53:34 GMT
• Title: MCAQ-YOLO: Morphological Complexity-Aware Quantization for Efficient Object Detection with Curriculum Learning
• Authors: Yoonjae Seo, Ermal Elbasani, Jaehong Lee,
• Abstract summary: MCAQ-YOLO is a morphological complexity-aware quantization framework for object detection.<n>By correlating morphological metrics with quantization sensitivity, MCAQ-YOLO dynamically adjusts bit precision according to spatial complexity.<n>On a safety equipment dataset, MCAQ-YOLO attains 85.6% mAP@0.5 with an average of 4.2 bits and a 7.6x compression ratio.
• Score: 12.577630686466675
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Physically Interpretable Representation Learning with Gaussian Mixture Variational AutoEncoder (GM-VAE) [37.18249990338269]
  We propose a Variational Autoencoder (GM-VAE) framework designed to extract, physically interpretable representations from high-dimensional scientific data.<n>Unlike conventional VAEs that jointly optimize reconstruction and clustering, our method utilizes a block-coordinate descent strategy.<n>To objectively evaluate the learned representations, we introduce a metric based on graph-Laplacian smoothness, which measures the coherence of physical instability across the latent manifold.
  arXiv  Detail & Related papers  (2025-11-26T20:04:38Z)
• Constrained Shadow Tomography for Molecular Simulation on Quantum Devices [11.572076686962106]
  We introduce a bi-objective semidefinite programming approach for constrained shadow tomography.<n>The method builds an $N$-representable 2-RDM that balances fidelity to the shadow measurements with energy minimization.<n> Numerical and hardware results demonstrate that the approach significantly improves accuracy, noise resilience, and scalability.
  arXiv  Detail & Related papers  (2025-11-12T20:24:43Z)
• SDTN and TRN: Adaptive Spectral-Spatial Feature Extraction for Hyperspectral Image Classification [1.2871580250533408]
  Hyperspectral image classification plays a pivotal role in precision agriculture, providing accurate insights into crop health monitoring, disease detection, and soil analysis.<n>Traditional methods struggle with high-dimensional data, spectral-spatial redundancy, and the scarcity of labeled samples, often leading to suboptimal performance.<n>To address these challenges, we propose the Self-Adaptive- Regularized Network (SDTN), which combines tensor decomposition with regularization mechanisms to dynamically adjust tensor ranks.<n>This approach not only maintains high classification accuracy but also significantly reduces computational complexity, making the framework highly suitable for real-time deployment in resource-constrained environments.
  arXiv  Detail & Related papers  (2025-07-13T04:53:33Z)
• Structure and asymptotic preserving deep neural surrogates for uncertainty quantification in multiscale kinetic equations [5.181697052513637]
  High dimensionality of kinetic equations with parameters poses computational challenges for uncertainty quantification (UQ)<n>Traditional Monte Carlo (MC) sampling methods suffer from slow convergence and high variance, which become increasingly severe as the dimensionality of the space grows.<n>We introduce surrogate models based on structure and preserving neural networks (SAPNNs)<n>SAPNNs are specifically designed to satisfy key physical properties, including positivity, conservation laws, entropy dissipation, parameter limits.
  arXiv  Detail & Related papers  (2025-06-12T12:20:53Z)
• HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization [55.972018549438964]
  Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy.<n>We propose HAFLQ (Heterogeneous Adaptive Federated Low-Rank Adaptation Fine-tuned LLM with Quantization), a novel framework for efficient and scalable fine-tuning of LLMs in heterogeneous environments.<n> Experimental results on the text classification task demonstrate that HAFLQ reduces memory usage by 31%, lowers communication cost by 49%, improves accuracy by 50%, and achieves faster convergence compared to the baseline method.
  arXiv  Detail & Related papers  (2024-11-10T19:59:54Z)
• DeepMpMRI: Tensor-decomposition Regularized Learning for Fast and High-Fidelity Multi-Parametric Microstructural MR Imaging [9.223502532342298]
  This paper proposes DeepMpMRI, an efficient framework for fast and high-fidelity multiple microstructural parameter estimation from multiple models.<n>DeepMpMRI is equipped with a newly designed tensor-decomposition-based regularizer to effectively capture fine details by exploiting the high-dimensional correlation across microstructural parameters.<n> Experimental results on the HCP dataset and the Alzheimer's disease dataset both demonstrate the superiority of our approach over 5 state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-06T04:36:02Z)
• GLCM-Based Feature Combination for Extraction Model Optimization in Object Detection Using Machine Learning [0.0]
  This research aims to enhance computational efficiency by selecting appropriate features within the GLCM framework. Two classification models, namely K-Nearest Neighbours (K-NN) and Support Vector Machine (SVM), were employed. The results indicate that K-NN outperforms SVM in terms of computational complexity.
  arXiv  Detail & Related papers  (2024-04-06T10:16:33Z)
• ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution [76.7408734079706]
  Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. We propose ESSAformer, an ESSA attention-embedded Transformer network for single-HSI-SR with an iterative refining structure.
  arXiv  Detail & Related papers  (2023-07-26T07:45:14Z)
• CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification [51.81850995661478]
  Mixed-precision quantization has been widely applied on deep neural networks (DNNs) Previous attempts on bit-level regularization and pruning-based dynamic precision adjustment during training suffer from noisy gradients and unstable convergence. We propose Continuous Sparsification Quantization (CSQ), a bit-level training method to search for mixed-precision quantization schemes with improved stability.
  arXiv  Detail & Related papers  (2022-12-06T05:44:21Z)
• Neural Networks with Quantization Constraints [111.42313650830248]
  We present a constrained learning approach to quantization training. We show that the resulting problem is strongly dual and does away with gradient estimations. We demonstrate that the proposed approach exhibits competitive performance in image classification tasks.
  arXiv  Detail & Related papers  (2022-10-27T17:12:48Z)
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors. Novel mixed precision neural network LM quantization methods are proposed in this paper.
  arXiv  Detail & Related papers  (2021-11-29T12:24:02Z)
• Mixed Precision of Quantization of Transformer Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Current low-bit quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of the system to quantization errors. The optimal local precision settings are automatically learned using two techniques. Experiments conducted on Penn Treebank (PTB) and a Switchboard corpus trained LF-MMI TDNN system.
  arXiv  Detail & Related papers  (2021-11-29T09:57:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.