Attributes Shape the Embedding Space of Face Recognition Models

• URL: http://arxiv.org/abs/2507.11372v1
• Date: Tue, 15 Jul 2025 14:44:39 GMT
• Title: Attributes Shape the Embedding Space of Face Recognition Models
• Authors: Pierrick Leroy, Antonio Mastropietro, Marco Nurisso, Francesco Vaccarino,
• Abstract summary: Face Recognition tasks have made significant progress with the advent of Deep Neural Networks.<n>We observe a multiscale geometric structure emerging in the embedding space.<n>We propose a geometric approach to describe the dependence or invariance of FR models to these attributes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into high-dimensional feature spaces. During training, these contrastive losses focus exclusively on identity information as labels. However, we observe a multiscale geometric structure emerging in the embedding space, influenced by interpretable facial (e.g., hair color) and image attributes (e.g., contrast). We propose a geometric approach to describe the dependence or invariance of FR models to these attributes and introduce a physics-inspired alignment metric. We evaluate the proposed metric on controlled, simplified models and widely used FR models fine-tuned with synthetic data for targeted attribute augmentation. Our findings reveal that the models exhibit varying degrees of invariance across different attributes, providing insight into their strengths and weaknesses and enabling deeper interpretability. Code available here: https://github.com/mantonios107/attrs-fr-embs}{https://github.com/mantonios107/attrs-fr-embs

Related papers

• Cross-Modal Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognition [4.196626042312499]
  We propose a novel framework that redefines 3D place recognition through density-agnostic geometric reasoning.<n>Specifically, we introduce an implicit 3D representation based on elastic points, which is immune to the interference of original scene point cloud density.<n>With the aid of these two types of information, we obtain descriptors that fuse geometric information from both bird's-eye view and 3D segment perspectives.
  arXiv  Detail & Related papers  (2025-06-17T07:04:07Z)
• A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification [56.10719736365069]
  We extend the notion of expressivity, defined as the mutual information between learned features and specific attributes, to quantify how strongly attributes are encoded.<n>We find that BMI consistently shows the highest expressivity in the final layers, indicating its dominant role in recognition.<n>These findings demonstrate the central role of body attributes in ReID and establish a principled approach for uncovering attribute driven correlations.
  arXiv  Detail & Related papers  (2025-03-09T05:15:54Z)
• How to Squeeze An Explanation Out of Your Model [13.154512864498912]
  This paper proposes an approach for interpretability that is model-agnostic.<n>By including an SE block prior to the classification layer of any model, we are able to retrieve the most influential features.<n>Results show that this new SE-based interpretability can be applied to various models in image and video/multi-modal settings.
  arXiv  Detail & Related papers  (2024-12-06T15:47:53Z)
• SC2GAN: Rethinking Entanglement by Self-correcting Correlated GAN Space [16.040942072859075]
  Gene Networks that achieve following editing directions for one attribute could result in entangled changes with other attributes. We propose a novel framework SC$2$GAN disentanglement by re-projecting low-density latent code samples in the original latent space.
  arXiv  Detail & Related papers  (2023-10-10T14:42:32Z)
• Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification [78.52704557647438]
  We propose a novel FIne-grained Representation and Recomposition (FIRe$2$) framework to tackle both limitations without any auxiliary annotation or data. Experiments demonstrate that FIRe$2$ can achieve state-of-the-art performance on five widely-used cloth-changing person Re-ID benchmarks.
  arXiv  Detail & Related papers  (2023-08-21T12:59:48Z)
• Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning [52.506434446439776]
  Compositional zero-shot learning (CZSL) aims to recognize compositions with prior knowledge of known primitives (attribute and object) We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL.
  arXiv  Detail & Related papers  (2023-08-08T03:24:21Z)
• F?D: On understanding the role of deep feature spaces on face generation evaluation [5.655130837404874]
  We study the effect that different deep features and their design choices have on a perceptual metric. A key component of our analysis is the creation of synthetic counterfactual faces using deep face generators.
  arXiv  Detail & Related papers  (2023-05-31T17:21:58Z)
• Adaptive Face Recognition Using Adversarial Information Network [57.29464116557734]
  Face recognition models often degenerate when training data are different from testing data. We propose a novel adversarial information network (AIN) to address it.
  arXiv  Detail & Related papers  (2023-05-23T02:14:11Z)
• Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing [71.19528222206088]
  We propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation for face parsing. Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection. Our method achieves the new state-of-the-art performance on the Helen, CelebA-HQ, and LapaMask datasets.
  arXiv  Detail & Related papers  (2022-03-28T02:12:30Z)
• A-FMI: Learning Attributions from Deep Networks via Feature Map Importance [58.708607977437794]
  Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs) The redundancy of attribution features and the gradient saturation problem are challenges that attribution methods still face. We propose a new concept, feature map importance (FMI), to refine the contribution of each feature map, and a novel attribution method via FMI, to address the gradient saturation problem.
  arXiv  Detail & Related papers  (2021-04-12T14:54:44Z)
• IntroVAC: Introspective Variational Classifiers for Learning Interpretable Latent Subspaces [6.574517227976925]
  IntroVAC learns interpretable latent subspaces by exploiting information from an additional label. We show that IntroVAC is able to learn meaningful directions in the latent space enabling fine manipulation of image attributes.
  arXiv  Detail & Related papers  (2020-08-03T10:21:41Z)

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.