DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching

• URL: http://arxiv.org/abs/2609.16149v1
• Date: Mon, 14 Sep 2026 18:00:44 GMT
• Title: DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching
• Abstract summary: We introduce a method that reduces racial bias in pre-trained face recognition models without compromising accuracy.<n>DenseFace preserves recognition accuracy and requires no retraining of the underlying face recognition model.<n>Our work also investigates previously adopted bias measures and makes suggestions.
• Score: 18.786403110326038
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite steady progress in face recognition, current face recognition models still suffer from significant demographic biases. While approaches for bias mitigation have been proposed, existing methods often impose constraints on the training procedure and result in the degradation of recognition accuracy. To address this issue, we here introduce a method that reduces racial bias in pre-trained face recognition models without compromising their accuracy. To this end, we model face embeddings of each person by von Mises-Fisher (MF) distribution. We next observe the dependency between demographic attributes and the density of MF distributions, and propose DenseFace, a probabilistic face matching procedure that accounts for differences in MF distributions. Our extensive experiments demonstrate DenseFace to consistently reduce racial bias in strong face recognition models varying in network architectures, training datasets and loss functions. Notably, DenseFace preserves recognition accuracy and requires no retraining of the underlying face recognition model. Our work also investigates previously adopted bias measures and makes suggestions.

Related papers

• MoDE: Mixture of Diffusion Experts for Any Occluded Face Recognition [0.0]
  We propose an identity-gated mixture of diffusion experts (MoDE) for OFR.<n>To ensemble effective information from multi-reconstructed faces, we introduce an identity-gating network.<n>Our MoDE is a plug-and-play module for most existing face recognition models.
  arXiv  Detail & Related papers  (2025-05-07T10:29:39Z)
• Local Features Meet Stochastic Anonymization: Revolutionizing Privacy-Preserving Face Recognition for Black-Box Models [54.88064975480573]
  The task of privacy-preserving face recognition (PPFR) currently faces two major unsolved challenges.<n>By disrupting global features while enhancing local features, we achieve effective recognition even in black-box environments.<n>Our method achieves an average recognition accuracy of 94.21% on black-box models, outperforming existing methods in both privacy protection and anti-reconstruction capabilities.
  arXiv  Detail & Related papers  (2024-12-11T10:49:15Z)
• OSDFace: One-Step Diffusion Model for Face Restoration [72.5045389847792]
  Diffusion models have demonstrated impressive performance in face restoration.<n>We propose OSDFace, a novel one-step diffusion model for face restoration.<n>Results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics.
  arXiv  Detail & Related papers  (2024-11-26T07:07:48Z)
• Watch Out for the Confusing Faces: Detecting Face Swapping with the Probability Distribution of Face Identification Models [37.49012763328351]
  We propose a novel face swapping detection approach based on face identification probability distributions. IdP_FSD is specially designed for detecting swapped faces whose identities belong to a finite set. IdP_FSD exploits face swapping's common nature that the identity of swapped face combines that of two faces involved in swapping.
  arXiv  Detail & Related papers  (2023-03-23T09:33:10Z)
• Controllable Inversion of Black-Box Face Recognition Models via Diffusion [8.620807177029892]
  We tackle the task of inverting the latent space of pre-trained face recognition models without full model access. We show that the conditional diffusion model loss naturally emerges and that we can effectively sample from the inverse distribution. Our method is the first black-box face recognition model inversion method that offers intuitive control over the generation process.
  arXiv  Detail & Related papers  (2023-03-23T03:02:09Z)
• Are Face Detection Models Biased? [69.68854430664399]
  We investigate possible bias in the domain of face detection through facial region localization. Most existing face detection datasets lack suitable annotation for such analysis. We observe a high disparity in detection accuracies across gender and skin-tone, and interplay of confounding factors beyond demography.
  arXiv  Detail & Related papers  (2022-11-07T14:27:55Z)
• Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition [107.58227666024791]
  Face recognition systems are widely deployed in safety-critical applications, including law enforcement. They exhibit bias across a range of socio-demographic dimensions, such as gender and race. Previous works on bias mitigation largely focused on pre-processing the training data.
  arXiv  Detail & Related papers  (2022-10-18T15:46:05Z)
• End2End Occluded Face Recognition by Masking Corrupted Features [82.27588990277192]
  State-of-the-art general face recognition models do not generalize well to occluded face images. This paper presents a novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network. Our approach, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks.
  arXiv  Detail & Related papers  (2021-08-21T09:08:41Z)
• Learning Fair Face Representation With Progressive Cross Transformer [79.73754444296213]
  We propose a progressive cross transformer (PCT) method for fair face recognition. We show that PCT is capable of mitigating bias in face recognition while achieving state-of-the-art FR performance.
  arXiv  Detail & Related papers  (2021-08-11T01:31:14Z)
• BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions [25.00475462213752]
  We present BioMetricNet, a novel framework for deep unconstrained face verification. The proposed approach does not impose any specific metric on facial features. It shapes the decision space by learning a latent representation in which matching and non-matching pairs are mapped onto clearly separated and well-behaved target distributions.
  arXiv  Detail & Related papers  (2020-08-13T17:22:46Z)

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.