Are Face Embeddings Compatible Across Deep Neural Network Models?

• URL: http://arxiv.org/abs/2604.07282v1
• Date: Wed, 08 Apr 2026 16:44:42 GMT
• Title: Are Face Embeddings Compatible Across Deep Neural Network Models?
• Abstract summary: We study whether different deep neural network (DNN) models can align face representations of one model with another.<n>Our findings reveal surprising cross-model compatibility.<n>These findings have implications for model interoperability, ensemble design, and biometric template security.
• Score: 8.929662625846595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated face recognition has made rapid strides over the past decade due to the unprecedented rise of deep neural network (DNN) models that can be trained for domain-specific tasks. At the same time, foundation models that are pretrained on broad vision or vision-language tasks have shown impressive generalization across diverse domains, including biometrics. This raises an important question: Do different DNN models--both domain-specific and foundation models--encode facial identity in similar ways, despite being trained on different datasets, loss functions, and architectures? In this regard, we directly analyze the geometric structure of embedding spaces imputed by different DNN models. Treating embeddings of face images as point clouds, we study whether simple affine transformations can align face representations of one model with another. Our findings reveal surprising cross-model compatibility: low-capacity linear mappings substantially improve cross-model face recognition over unaligned baselines for both face identification and verification tasks. Alignment patterns generalize across datasets and vary systematically across model families, indicating representational convergence in facial identity encoding. These findings have implications for model interoperability, ensemble design, and biometric template security.

Related papers

• Unmasking Face Embeddings: Reading, Rendering and Naming with Foundation Models [8.929662625846595]
  Building on recent work on embedding compatibility across models, we use simple pre-computed linear transformations to connect FR models with off-the-shelf foundation models.<n>This interoperability exposes face embeddings as semantically and visually rich biometric representations, with implications for interpretability, retrieval, reconstruction, and template security.
  arXiv  Detail & Related papers  (2026-08-31T21:46:54Z)
• Connecting Neural Models Latent Geometries with Relative Geodesic Representations [21.71782603770616]
  We show that when a latent structure is shared between distinct latent spaces, relative distances between representations can be preserved, up to distortions.<n>We assume that distinct neural models parametrize approximately the same underlying manifold, and introduce a representation based on the pullback metric.<n>We validate our method on model stitching and retrieval tasks, covering autoencoders and vision foundation discriminative models.
  arXiv  Detail & Related papers  (2025-06-02T12:34:55Z)
• Sequential Modeling Enables Scalable Learning for Large Vision Models [120.91839619284431]
  We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. We define a common format, "visual sentences", in which we can represent raw images and videos as well as annotated data sources.
  arXiv  Detail & Related papers  (2023-12-01T18:59:57Z)
• Modeling biological face recognition with deep convolutional neural networks [0.0]
  Deep convolutional neural networks (DCNNs) have become the state-of-the-art computational models of biological object recognition. Recent efforts have started to transfer this achievement to research on biological face recognition. In this review, we summarize the first studies that use DCNNs to model biological face recognition.
  arXiv  Detail & Related papers  (2022-08-13T16:45:30Z)
• Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis [8.20832544370228]
  We introduce a domain-agnostic architecture to study any surface data projected onto a spherical manifold. A vision transformer model encodes the sequence of patches via successive multi-head self-attention layers. Experiments show that the SiT generally outperforms surface CNNs, while performing comparably on registered and unregistered data.
  arXiv  Detail & Related papers  (2022-03-30T15:56:11Z)
• 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)
• Multi-Branch Deep Radial Basis Function Networks for Facial Emotion Recognition [80.35852245488043]
  We propose a CNN based architecture enhanced with multiple branches formed by radial basis function (RBF) units. RBF units capture local patterns shared by similar instances using an intermediate representation. We show it is the incorporation of local information what makes the proposed model competitive.
  arXiv  Detail & Related papers  (2021-09-07T21:05:56Z)
• The FaceChannel: A Fast & Furious Deep Neural Network for Facial Expression Recognition [71.24825724518847]
  Current state-of-the-art models for automatic Facial Expression Recognition (FER) are based on very deep neural networks that are effective but rather expensive to train. We formalize the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks. We demonstrate how our model achieves a comparable, if not better, performance to the current state-of-the-art in FER.
  arXiv  Detail & Related papers  (2020-09-15T09:25:37Z)
• InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs [73.27299786083424]
  We propose a framework called InterFaceGAN to interpret the disentangled face representation learned by state-of-the-art GAN models. We first find that GANs learn various semantics in some linear subspaces of the latent space. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection.
  arXiv  Detail & Related papers  (2020-05-18T18:01:22Z)
• A Detailed Look At CNN-based Approaches In Facial Landmark Detection [5.774786149181392]
  CNN-based approaches can be divided into regression and heatmap approaches. In this paper, we investigate both CNN-based approaches, generalize their advantages and disadvantages, and introduce a variation of the heatmap approach. A comprehensive evaluation is conducted and the result shows that the proposed model outperforms other models in all tested datasets.
  arXiv  Detail & Related papers  (2020-05-08T16:17:42Z)
• Learning Formation of Physically-Based Face Attributes [16.55993873730069]
  Based on a combined data set of 4000 high resolution facial scans, we introduce a non-linear morphable face model. Our deep learning based generative model learns to correlate albedo and geometry, which ensures the anatomical correctness of the generated assets.
  arXiv  Detail & Related papers  (2020-04-02T07:01:30Z)
• DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition [94.96686189033869]
  We propose a 3D model-assisted domain-transferred face augmentation network (DotFAN) DotFAN can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected from other domains. Experiments show that DotFAN is beneficial for augmenting small face datasets to improve their within-class diversity.
  arXiv  Detail & Related papers  (2020-02-23T08:16:34Z)

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.