Learning Steadily: Accumulating Relative Point Margin Scores for Face Image Quality Assessment
Authors: Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira, Marco Huber, Jan Niklas Kolf, Naser Damer, Fadi Boutros
Organizations: Fraunhofer Institute for Computer Graphics Research IGD, Fraunhoferstr. 5, 64283 Darmstadt, Germany · Department of Computer Science at the TU Darmstadt, Karolinenpl. 5, 64289 Darmstadt, Germany
Face Image Quality Assessment determines the suitability of captured face images for automated face recognition (FR), a critical capability for reliable biometric systems. Existing state-of-the-art FR-integrated FIQA methods suffer from temporal instability: as the feature space evolves during training, single-epoch quality estimates fluctuate, creating a moving target that undermines reliable quality prediction. We introduce CARPM-FIQA, a stabilization strategy for FR-integrated FIQA that accumulates relative point margin measurements, the ratio between intra-class compactness and inter-class separation, across the entire training trajectory rather than relying on single-epoch estimates. This cumulative averaging approach provides theoretically grounded advantages: reduced variance in quality estimates, improved mean squared error, and enhanced ranking stability with convergence guarantees as training progresses. Through controlled experiments on the SynFIQA dataset with labeled quality groups, we demonstrate that cumulative averaging achieves superior discriminative ability, and ablation studies across different training configurations confirm consistent improvements. Evaluated against twelve FIQA methods on eight challenging benchmarks with four FR models at two FMR thresholds, CARPM-FIQA places 4th (CARPM-FIQA(L)) and 6th (CARPM-FIQA(S)) of 17 compared methods by pAUC-EDC and AUC-EDC averaged across FR models and, after per-benchmark normalization, across benchmarks, staying within a few percent of the best method's normalized average for every FR model, providing a principled solution to training instability while maintaining the performance benefits of FR integration. More broadly, our work demonstrates that temporal aggregation strategies can stabilize training objectives in deep learning systems where target values inherently fluctuate due to evolving feature representations.
Figures & tables
Fig. 1: Normalized quality score distributions for 11 quality groups, each having 0.5M images, from 5.5M images of SynFIQA [ 1 ] . (Q0-Q9: degraded images from lowest to highest quality; Ref: reference images) comparing non-cumulative (top) and cumulative (bottom) methods. Scores are z-score normalized within each method. Color gradient from red to green indicates quality progression. Cohen’s d effect sizes between adjacent groups are reported. The cumulative method achieves higher average Cohen’s d (0.3112 vs. 0.2514) on the small protocol (ArcFace/ResNet50/CASIA-WebFace), demonstrating a better group separation.
Fig. 2: High quality samples from identity #6987 across training epochs. Note how the top-ranked images in the non-cumulative approach (top) tend to stabilize in the cumulative approach (bottom), showing the benefit of averaging quality scores over time.
Fig. 3: Comparison of cumulative and non-cumulative quality estimation. (a) EDC curves and (b) AUC-EDC trends show cumulative averaging improves estimates consistently, while non-cumulative degrades after epoch 20. (c, d) Quality target distributions highlight non-cumulative compression versus cumulative stability.
Metric
FR
Quality Metric
Adience
AgeDB-30
CFP-FP
LFW
CALFW
CPLFW
XQLFW
Avg. norm.
[ 18 ]
[ 15 ]
[ 16 ]
[ 14 ]
[ 17 ]
[ 19 ]
[ 20 ]
1e−3
1e−4
1e−3
1e−4
1e−3
1e−4
1e−3
1e−4
1e−3
1e−4
1e−3
1e−4
1e−3
1e−4
AUC-EDC
ArcFace [ 22 ]
non-cumulative
23.938
56.259
17.593
22.133
6.792
10.693
1.688
2.155
57.384
61.981
39.313
56.546
260.345
312.863
1.052
cumulative
22.070
44.323
17.897
22.728
6.791
10.743
1.953
2.573
60.759
63.547
41.281
57.975
218.855
262.735
1.040
ElasticFace [ 23 ]
non-cumulative
26.439
49.392
17.313
18.149
7.707
11.052
1.402
2.074
55.857
57.723
38.517
51.568
241.643
263.596
1.083
cumulative
23.646
40.996
17.973
18.768
5.867
8.173
1.630
2.457
59.054
60.379
39.146
51.597
205.884
277.024
1.042
TABLE II: Comparison of AUC-EDC and pAUC-EDC (lower is better) under the same experimental setting as Tab. I , but with CurricularFace loss instead of ArcFace.
Fig. 4: Error-versus-Discard Characteristic (EDC) curves for FNMR@FMR= 1e−3 of our proposed method CARPM-FIQA in comparison to SOTA. Results shown on eight benchmark datasets: LFW [ 14 ] , AgeDB-30 [ 15 ] , CFP-FP [ 16 ] , CALFW [ 17 ] , Adience [ 18 ] , CPLFW [ 19 ] , XQLFW [ 20 ] , and IJB-C [ 21 ] , using ArcFace [ 22 ] , ElasticFace [ 23 ] , MagFace [ 10 ] , and CurricularFace [ 24 ] FR models.
Configuration
T
k @ ρ=0.95
k @ ρ=0.99
first- k
last- k
ArcFace, cumulative, small
34
10
24
0.939
0.845
ArcFace, non-cumulative, small
34
11
24
0.938
0.857
CurricularFace, cumulative, small
34
11
24
0.935
0.854
CurricularFace, non-cumulative, small
34
11
24
0.934
0.869
ArcFace, cumulative, large
18
8
14
0.876
0.841
ArcFace, non-cumulative, large
18
8
14
0.883
0.840
TABLE III: Influence of the accumulation window: window length k (of T training epochs) at which the growing first- k window reaches Spearman rank correlation ρ≥0.95 / 0.99 against the full-trajectory target QT , and Spearman correlation with QT of first- k vs. last- k windows at a matched relative window length ( k≈24% of T : k=8 of 34 for the small protocol, k=4 of 18 for the large).
Face Image Quality Assessment (FIQA) aims to assess the recognition utility of face samples and is essential for reliable face recognition (FR) systems. Existing approaches require computationally expensive procedures such as multiple forward passes, backpropagation, or additional training, and only recent work has focused on the use of Vision Transformers. Recent studies highlighted that these architectures inherently function as saliency learners with attention patterns naturally encoding spatial importance. This work proposes ATTN-FIQA, a novel training-free approach that investigates whether pre-softmax attention scores from pre-trained Vision Transformer-based face recognition models can serve as quality indicators. We hypothesize that attention magnitudes intrinsically encode quality: high-quality images with discriminative facial features enable strong query-key alignments producing focused, high-magnitude attention patterns, while degraded images generate diffuse, low-magnitude patterns. ATTN-FIQA extracts pre-softmax attention matrices from the final transformer block, aggregate multi-head attention information across all patches, and compute image-level quality scores through simple averaging, requiring only a single forward pass through pre-trained models without architectural modifications, backpropagation, or additional training. Through comprehensive evaluation across eight benchmark datasets and four FR models, this work demonstrates that attention-based quality scores effectively correlate with face image quality and provide spatial interpretability, revealing which facial regions contribute most to quality determination.
Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira +5
Fraunhofer Institute for Computer Graphics Research IGD, Darmstadt, Germany · Department of Computer Science, TU Darmstadt, Germany
Face Image Quality Assessment (FIQA) evaluates the utility of a face image for automated face recognition (FR) systems. In this work, we propose PreFIQs, an unsupervised and training-free FIQA framework grounded in the Pruning Identified Exemplar (PIE) hypothesis. We hypothesize that low-utility face images rely disproportionately on fragile network parameters, resulting in larger geometric displacement of their embeddings under model sparsification. Accordingly, PreFIQs quantifies image utility as the Euclidean distance between L2-normalized embeddings extracted from a pre-trained FR model and its pruned counterpart. We provide a first-order theoretical justification via a Jacobian-vector product analysis, demonstrating that this empirical drift serves as a computationally efficient approximation of the exact geometric sensitivity of the latent embedding manifold. Extensive experiments across eight benchmarks and four FR models demonstrate that PreFIQs achieves competitive or superior performance compared to state-of-the-art FIQA methods, including establishing new state-of-the-art results on several benchmarks, without any training or supervision. These results validate parameter sparsification as a principled and practically efficient signal for face image utility, and demonstrate that quality is, in essence, what survives pruning.
Jan Niklas Kolf, Guray Ozgur, Andrea Atzori +4
FRAUNHOFER INSTITUTE FOR COMPUTER GRAPHICS RESEARCH IGD, GERMANY · TECHNICAL UNIVERSITY OF DARMSTADT, GERMANY · UNIVERSITY OF LJUBLJANA, SLOVENIA
Face Image Quality Assessment (FIQA) aims to estimate the utility of facial images for reliable recognition. The evaluation of FIQA methods is predominantly based on the Error-versus-Discard Characteristic (EDC), which evaluates performance by progressively discarding low-quality samples and measuring recognition error on the retained subset. In this work, we demonstrate that the widely used EDC protocol has fundamental limitations: Test-Set Divergence and Threshold Drift, which together limit the reliability and comparability of FIQA methods. To address this, we propose discard-based EDC variants and a rank-based Rank Consistency Evaluation (RCE) metric that operates on the entire test set without discarding samples, using a fixed decision threshold. Extensive experiments on five datasets, four face recognition models, and 15 state-of-the-art FIQA methods demonstrate both the limitations of EDC and the effectiveness of the proposed approaches in enabling a more reliable and comparable evaluation. Despite evaluated on face images only, the limitations arise from the EDC protocol rather than the biometric modality, suggesting a broader applicability to biometric quality assessment in general.
Bhavesh Wani, Žiga Babnik, Vitomir Štruc +1
Johannes Gutenberg University Mainz, Germany · University of Ljubljana, Slovenia