Latent Feature Alignment: Discovering Biased and Interpretable Subpopulations in Face Recognition Models

• URL: http://arxiv.org/abs/2510.15520v1
• Date: Fri, 17 Oct 2025 10:49:50 GMT
• Title: Latent Feature Alignment: Discovering Biased and Interpretable Subpopulations in Face Recognition Models
• Abstract summary: Latent Feature Alignment (LFA) is an attribute-label-free algorithm that uses latent directions to identify subpopulations.<n>LFA consistently outperforms k-means and nearest-neighbor search in intra-group semantic coherence.<n>These results position LFA as a practical method for representation auditing of face recognition models.
• Score: 2.098253213160396
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Modern face recognition models achieve high overall accuracy but continue to exhibit systematic biases that disproportionately affect certain subpopulations. Conventional bias evaluation frameworks rely on labeled attributes to form subpopulations, which are expensive to obtain and limited to predefined categories. We introduce Latent Feature Alignment (LFA), an attribute-label-free algorithm that uses latent directions to identify subpopulations. This yields two main benefits over standard clustering: (i) semantically coherent grouping, where faces sharing common attributes are grouped together more reliably than by proximity-based methods, and (ii) discovery of interpretable directions, which correspond to semantic attributes such as age, ethnicity, or attire. Across four state-of-the-art recognition models (ArcFace, CosFace, ElasticFace, PartialFC) and two benchmarks (RFW, CelebA), LFA consistently outperforms k-means and nearest-neighbor search in intra-group semantic coherence, while uncovering interpretable latent directions aligned with demographic and contextual attributes. These results position LFA as a practical method for representation auditing of face recognition models, enabling practitioners to identify and interpret biased subpopulations without predefined attribute annotations.

Related papers

• RA-ClipScore: Making Generative Model Evaluation More Interpretable [10.211263272517911]
  We propose RA-CLIPScore, a novel metric for semantic evaluation of generative models.<n> RA-CLIPScore measures whether generated objects adhere to the positional priors found in the training data.<n>We show that RA-CLIPScore provides more robust and interpretable evaluations than prior methods.
  arXiv  Detail & Related papers  (2026-08-12T14:11:27Z)
• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• UniDGF: A Unified Detection-to-Generation Framework for Hierarchical Object Visual Recognition [14.256812146187565]
  We introduce a detection-guided generative framework that predicts hierarchical category and attribute tokens.<n>For each detected object, we extract refined ROI-level features and employ a BART-based generator to produce semantic tokens.<n> Experiments on both large-scale proprietary e-commerce datasets and open-source datasets demonstrate that our approach significantly outperforms existing similarity-based pipelines.
  arXiv  Detail & Related papers  (2025-11-20T02:37:43Z)
• Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction [36.73147151458588]
  We present a solution inspired by the human cognitive process for novel object understanding.<n>We propose ConGCD, which establishes primitive-oriented representations through high-level semantic reconstruction.<n>We implement dominant and contextual consensus units to capture class-discriminative patterns.
  arXiv  Detail & Related papers  (2025-08-14T15:11:22Z)
• Fair Deepfake Detectors Can Generalize [51.21167546843708]
  We show that controlling for confounders (data distribution and model capacity) enables improved generalization via fairness interventions.<n>Motivated by this insight, we propose Demographic Attribute-insensitive Intervention Detection (DAID), a plug-and-play framework composed of: i) Demographic-aware data rebalancing, which employs inverse-propensity weighting and subgroup-wise feature normalization to neutralize distributional biases; and ii) Demographic-agnostic feature aggregation, which uses a novel alignment loss to suppress sensitive-attribute signals.<n>DAID consistently achieves superior performance in both fairness and generalization compared to several state-of-the-art
  arXiv  Detail & Related papers  (2025-07-03T14:10:02Z)
• Leveraging vision-language models for fair facial attribute classification [19.93324644519412]
  General-purpose vision-language model (VLM) is a rich knowledge source for common sensitive attributes. We analyze the correspondence between VLM predicted and human defined sensitive attribute distribution. Experiments on multiple benchmark facial attribute classification datasets show fairness gains of the model over existing unsupervised baselines.
  arXiv  Detail & Related papers  (2024-03-15T18:37:15Z)
• A structured regression approach for evaluating model performance across intersectional subgroups [53.91682617836498]
  Disaggregated evaluation is a central task in AI fairness assessment, where the goal is to measure an AI system's performance across different subgroups. We introduce a structured regression approach to disaggregated evaluation that we demonstrate can yield reliable system performance estimates even for very small subgroups.
  arXiv  Detail & Related papers  (2024-01-26T14:21:45Z)
• Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification [80.98291772215154]
  Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labels. We propose a Neighbour Consistency guided Pseudo Label Refinement framework.
  arXiv  Detail & Related papers  (2022-11-30T09:39:57Z)
• Fairness via Adversarial Attribute Neighbourhood Robust Learning [49.93775302674591]
  We propose a principled underlineRobust underlineAdversarial underlineAttribute underlineNeighbourhood (RAAN) loss to debias the classification head.
  arXiv  Detail & Related papers  (2022-10-12T23:39:28Z)
• TransFA: Transformer-based Representation for Face Attribute Evaluation [87.09529826340304]
  We propose a novel textbftransformer-based representation for textbfattribute evaluation method (textbfTransFA) The proposed TransFA achieves superior performances compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-07-12T10:58:06Z)
• Inter-class Discrepancy Alignment for Face Recognition [55.578063356210144]
  We propose a unified framework calledInter-class DiscrepancyAlignment(IDA) IDA-DAO is used to align the similarity scores considering the discrepancy between the images and its neighbors. IDA-SSE can provide convincing inter-class neighbors by introducing virtual candidate images generated with GAN.
  arXiv  Detail & Related papers  (2021-03-02T08:20:08Z)
• Mitigating Face Recognition Bias via Group Adaptive Classifier [53.15616844833305]
  This work aims to learn a fair face representation, where faces of every group could be more equally represented. Our work is able to mitigate face recognition bias across demographic groups while maintaining the competitive accuracy.
  arXiv  Detail & Related papers  (2020-06-13T06:43:37Z)

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.