MSPT: A Lightweight Face Image Quality Assessment Method with Multi-stage Progressive Training

2025-08-10

AI Summary

To address the poor generalizability of conventional methods and the high computational cost of deep models—hindering practical deployment in facial image quality assessment—this paper proposes a lightweight convolutional neural network coupled with a three-stage progressive training strategy. The strategy incrementally increases input resolution and data diversity during training, effectively mitigating catastrophic forgetting in compact models and enhancing their capacity to learn complex quality-related features. Crucially, we embed the progressive learning mechanism directly into a streamlined architecture. Evaluated on the VQualA 2025 benchmark, our method ranks second, achieving performance on par with or surpassing existing state-of-the-art approaches, while significantly reducing model parameters and inference latency. This work thus delivers a favorable trade-off between accuracy and efficiency for real-world facial quality assessment.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurately assessing the perceptual quality of face images is crucial, especially with the rapid progress in face restoration and generation. Traditional quality assessment methods often struggle with the unique characteristics of face images, limiting their generalizability. While learning-based approaches demonstrate superior performance due to their strong fitting capabilities, their high complexity typically incurs significant computational and storage costs, hindering practical deployment. To address this, we propose a lightweight face quality assessment network with Multi-Stage Progressive Training (MSPT). Our network employs a three-stage progressive training strategy that gradually introduces more diverse data samples and increases input image resolution. This novel approach enables lightweight networks to achieve high performance by effectively learning complex quality features while significantly mitigating catastrophic forgetting. Our MSPT achieved the second highest score on the VQualA 2025 face image quality assessment benchmark dataset, demonstrating that MSPT achieves comparable or better performance than state-of-the-art methods while maintaining efficient inference.

Problem

• Assessing perceptual quality of face images accurately
• Overcoming limitations of traditional face quality assessment methods
• Reducing computational costs in learning-based quality assessment

Innovation

• Multi-stage progressive training strategy
• Lightweight network for quality assessment
• Gradual data diversity and resolution increase