# Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation arXiv: https://arxiv.org/abs/2507.15709 ยท HTML: https://mlsanity.com/paper/2507.15709/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation. - Builds on 40 of its 69 references that are in the map. - First posted on arXiv 21 Jul 2025. ## Placed in - Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/) ## Builds on (most cited first, 30 of 40) - [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021) - [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015) - [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018) - [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019) - [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021) - [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022) - [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018) - [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022) - [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023) - [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023) - [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019) - [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023) - [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016) - [A Deep Learning based No-reference Quality Assessment Model for UGC Videos](https://mlsanity.com/paper/2204.14047/) (2022) - [EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications](https://mlsanity.com/paper/2206.10589/) (2022) - [SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness](https://mlsanity.com/paper/2003.09373/) (2020) - [ARNIQA: Learning Distortion Manifold for Image Quality Assessment](https://mlsanity.com/paper/2310.14918/) (2023) - [Face Image Quality Assessment: A Literature Survey](https://mlsanity.com/paper/2009.01103/) (2020) - [Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training](https://mlsanity.com/paper/2105.14550/) (2021) - [SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance](https://mlsanity.com/paper/2103.05977/) (2021) - [FaceQnet: Quality Assessment for Face Recognition based on Deep Learning](https://mlsanity.com/paper/1904.01740/) (2019) - [MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos](https://mlsanity.com/paper/2303.14933/) (2023) - [LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models](https://mlsanity.com/paper/2408.14008/) (2024) - [Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos](https://mlsanity.com/paper/2106.01111/) (2021) - [Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation](https://mlsanity.com/paper/2307.02808/) (2023) - [Large Multi-modality Model Assisted AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2404.17762/) (2024) - [Going the Extra Mile in Face Image Quality Assessment: A Novel Database and Model](https://mlsanity.com/paper/2207.04904/) (2022) - [Enhancing Blind Video Quality Assessment with Rich Quality-aware Features](https://mlsanity.com/paper/2405.08745/) (2024) - [DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer](https://mlsanity.com/paper/2406.09622/) (2024) - [An Image Quality Assessment Dataset for Portraits](https://mlsanity.com/paper/2304.05772/) (2023) ## Built on by (most cited first, 3 of 3) - [VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results](https://mlsanity.com/paper/2508.18445/) (2025) - [LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning](https://mlsanity.com/paper/2606.29752/) (2026) - [DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble](https://mlsanity.com/paper/2607.00416/) (2026) ## Abstract (arXiv) Face image quality assessment (FIQA) is essential for various face-related applications. Although FIQA has been extensively studied and achieved significant progress, the computational complexity of FIQA algorithms remains a key concern for ensuring scalability and practical deployment in real-world systems. In this paper, we aim to develop a computationally efficient FIQA method that can be easily deployed in real-world applications. Specifically, our method consists of two stages: training a powerful teacher model and distilling a lightweight student model from it. To build a strong teacher model, we adopt a self-training strategy to improve its capacity. We first train the teacher model using labeled face images, then use it to generate pseudo-labels for a set of unlabeled images. These pseudo-labeled samples are used in two ways: (1) to distill knowledge into the student model, and (2) to combine with the original labeled images to further enhance the teacher model through self-training. The enhanced teacher model is used to further pseudo-label another set of unlabeled images for distilling the student models. The student model is trained using a combination of labeled images, pseudo-labeled images from the original teacher model, and pseudo-labeled images from the enhanced teacher model. Experimental results demonstrate that our student model achieves comparable performance to the teacher model with an extremely low computational overhead. Moreover, our method achieved first place in the ICCV 2025 VQualA FIQA Challenge. The code is available at https://github.com/sunwei925/Efficient-FIQA.git.