FaceMoE: Mixture of Experts for Low-Resolution Face Recognition

• URL: http://arxiv.org/abs/2606.32040v1
• Date: Tue, 30 Jun 2026 17:59:57 GMT
• Title: FaceMoE: Mixture of Experts for Low-Resolution Face Recognition
• Abstract summary: We propose FaceMoE, an effective adaptation of Mixture of Experts (MoE) transfomer architecture for low-resolution face-recognition.<n>Specifically, we introduce multiple specialized feed-forward network (FFN) experts and incorporate a top-k router, which dynamically assigns tokens to appropriate experts.<n>This design emergently promotes specialization across experts for different semantic regions of the face, which enables FaceMoE to perform resolution-aware feature extraction.
• Score: 54.04077186145988
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-resolution face recognition (LR-FR) remains a challenging task due to poor feature extraction and aggregation, as probe images often contain limited identity information resulting from extreme degradations such as blur, occlusion, and low contrast. Additionally, the domain gap between high-resolution (HR) gallery images and low-resolution (LR) probe images poses a significant challenge. A single feature encoder struggles to generalize effectively across both domains when fine-tuned on an LR dataset, and this issue is further magnified by catastrophic forgetting. To address these challenges, we propose FaceMoE, an effective adaptation of Mixture of Experts (MoE) transfomer architecture for low-resolution face-recognition . Specifically, we introduce multiple specialized feed-forward network (FFN) experts and incorporate a top-k router, which dynamically assigns tokens to appropriate experts. This design emergently promotes specialization across experts for different semantic regions of the face, which enables FaceMoE to perform resolution-aware feature extraction. Moreover, the top-k router facilitates sparse expert activation, enabling the model to preserve pretrained knowledge when finetuned on a LR dataset, while increasing model capacity without proportional computational overhead. FaceMoE is trained with a combined face recognition loss, router z-loss, and load balancing loss to ensure expert specialization and stable training. To the best of our knowledge, this is the first work leveraging MoE for LR-FR. Extensive experiments across eleven datasets, spanning HR, mixed-quality, and LR benchmarks, demonstrate that FaceMoE significantly outperforms state-of-the-art methods. Code: https://github.com/Kartik-3004/FaceMoE

Related papers

• Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution [76.66229730098759]
  In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models.<n>We propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution.<n>We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert.
  arXiv  Detail & Related papers  (2025-11-20T04:11:44Z)
• ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization [13.182475975397251]
  ERMoE is a sparse MoE transformer that replaces learned gating logits with an "Eigenbasis Score"<n>We show that ERMoE achieves state-of-the-art accuracy on ImageNet classification and cross-modal image-text retrieval benchmarks.<n>A 3D MRI variant (ERMoE-ba) improves brain age prediction accuracy by more than 7% and yields interpretable expert specializations.
  arXiv  Detail & Related papers  (2025-11-14T05:31:37Z)
• MoFRR: Mixture of Diffusion Models for Face Retouching Restoration [36.309979915418296]
  Face Retouching Restoration (FRR) is a novel computer vision task aimed at restoring original faces from retouched counterparts.<n>MoFRR uses sparse activation of specialized experts handling distinct retouching types and the engagement of a shared expert dealing with universal retouching traces.<n>Experiments on a newly constructed face retouching dataset, RetouchingFFHQ++, demonstrate the effectiveness of MoFRR for FRR.
  arXiv  Detail & Related papers  (2025-07-26T03:45:53Z)
• Heterogeneous Mixture of Experts for Remote Sensing Image Super-Resolution [23.383837540690823]
  We introduce a Mixture of Experts (MoE) model and design a set of heterogeneous experts.<n>These experts are organized into multiple expert groups, where experts within each group are homogeneous while being heterogeneous across groups.<n> Experiments conducted on the UCMerced and AID datasets demonstrate that our proposed method achieves superior SR reconstruction accuracy.
  arXiv  Detail & Related papers  (2025-02-12T03:25:53Z)
• See More Details: Efficient Image Super-Resolution by Experts Mining [79.35310245195402]
  We introduce SeemoRe, an efficient SR model employing expert mining. Our approach strategically incorporates experts at different levels, adopting a collaborative methodology. By tapping into experts specialized in distinct key factors crucial for accurate SR, our model excels in uncovering intricate intra-feature details.
  arXiv  Detail & Related papers  (2024-02-05T16:11:04Z)
• Balancing Efficiency and Quality: MoEISR for Arbitrary-Scale Image Super-Resolution [11.256166497045792]
  We introduce a novel and efficient framework, the Mixture-of-Experts Implicit Super-Resolution (MoEISR)<n>MoEISR dynamically allocates the most suitable decoding expert to each pixel using a lightweight mapper module.<n>Our experiments demonstrate that MoEISR successfully reduces significant amount of floating point operations (FLOPs) while delivering comparable or superior peak signal-to-noise ratio (PSNR)
  arXiv  Detail & Related papers  (2023-11-20T05:34:36Z)
• Best-Buddy GANs for Highly Detailed Image Super-Resolution [71.13466303340192]
  We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input. Most methods along this line rely on a predefined single-LR-single-HR mapping, which is not flexible enough for the SISR task. We propose best-buddy GANs (Beby-GAN) for rich-detail SISR. Relaxing the immutable one-to-one constraint, we allow the estimated patches to dynamically seek the best supervision.
  arXiv  Detail & Related papers  (2021-03-29T02:58:27Z)
• Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition [59.29808528182607]
  Cross-resolution face recognition (CRFR) is important in intelligent surveillance and biometric forensics. Existing shallow learning-based and deep learning-based methods focus on mapping the HR-LR face pairs into a joint feature space. In this study, we desire to fully exploit the multi-level deep convolutional neural network (CNN) feature set for robust CRFR.
  arXiv  Detail & Related papers  (2021-03-25T14:03:42Z)
• Recurrent Exposure Generation for Low-Light Face Detection [113.25331155337759]
  We propose a novel Recurrent Exposure Generation (REG) module and a Multi-Exposure Detection (MED) module. REG produces progressively and efficiently intermediate images corresponding to various exposure settings. Such pseudo-exposures are then fused by MED to detect faces across different lighting conditions.
  arXiv  Detail & Related papers  (2020-07-21T17:30:51Z)
• Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution [31.934084942626257]
  We propose a deep Super-Resolution Residual Convolutional Generative Adversarial Network (SRResCGAN) It follows the real-world degradation settings by adversarial training the model with pixel-wise supervision in the HR domain from its generated LR counterpart. The proposed network exploits the residual learning by minimizing the energy-based objective function with powerful image regularization and convex optimization techniques.
  arXiv  Detail & Related papers  (2020-05-03T00:12:38Z)

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.