ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation

• URL: http://arxiv.org/abs/2606.12023v1
• Date: Wed, 10 Jun 2026 12:46:39 GMT
• Title: ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation
• Abstract summary: Vision Transformers (ViTs) have gained significant attention in computer vision and shown strong potential for face recognition (FR)<n>In this work, we investigate early exiting in pretrained ViTs as a simple yet effective training-free strategy for efficient FR inference.<n>We introduce ViT-FREE, a multi-exit framework that enables face verification directly from intermediate representations without modifying or retraining the backbone model.
• Score: 16.250163286204593
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision Transformers (ViTs) have gained significant attention in computer vision and shown strong potential for face recognition (FR). However, their high computational cost makes deployment on resource-constrained devices challenging, motivating the need for methods that balance efficiency and accuracy. In this work, we investigate early exiting in pretrained ViTs as a simple yet effective training-free strategy for efficient FR inference. Leveraging the uniform feature dimensionality across transformer encoder blocks, we introduce ViT-FREE, a multi-exit framework that enables face verification directly from intermediate representations without modifying or retraining the backbone model, and thus, reducing inference cost. Empirically, we show that patch embeddings and attention maps evolve progressively across depth, exhibiting high similarity between consecutive ViT blocks and increasing alignment with the final representation. This indicates gradual feature refinement and attention convergence, suggesting that intermediate layers already provide stable and discriminative representations suitable for early exiting. Through extensive experiments on multiple FR benchmarks, we systematically analyze the accuracy-efficiency trade-off across exit depths. Our results demonstrate that later exits achieve a highly favorable balance, with exiting at layer 10 yielding up to a 20% speedup while incurring only a 1.5 drop in verification performance on benchmarks such as IJB-C. Also, we propose ViT-FREE_FT, a lightweight exit-specific fine-tuning strategy that adapts only the projection layers using a small synthetic dataset while keeping the transformer backbone frozen. This approach improves the performance of shallow exits while preserving the efficiency benefits and leaving deeper exits largely unaffected.

Related papers

• RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT [0.014257559724536567]
  Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.<n>We propose a depth-aware token reduction framework that adapts reduction strategies to the layer-wise characteristics of token representations.<n>Our framework provides a training-free template for optimizing vision models by aligning reduction strategies with hierarchical feature evolution.
  arXiv  Detail & Related papers  (2026-06-06T13:13:02Z)
• Accelerating Vision Foundation Models with Drop-in Depthwise Convolution [51.50107862675191]
  We introduce an efficient depthwise convolution-based layer that serves as a drop-in replacement for attention heads.<n>Across both image classification and segmentation tasks, our method achieves 17-20% percent inference speedup with minimal performance degradation.
  arXiv  Detail & Related papers  (2026-05-21T08:07:23Z)
• RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers [14.876863939653548]
  We reveal that feedforward network (FFN) layers, rather than attention layers, are the primary contributors to Vision Transformer (ViT) inference latency.<n>We propose a novel channel idle mechanism that facilitates post-training structural re parameterization for efficient FFN layers during testing.
  arXiv  Detail & Related papers  (2025-05-28T00:27:18Z)
• Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping [13.846838416902575]
  A key bottleneck stems from the proliferation of visual tokens required for fine-grained image understanding.<n>We propose Skip-Vision, a unified framework addressing both training and inference inefficiencies in vision-language models.<n> Experimental results demonstrate that Skip-Vision reduces training time by up to 35%, inference FLOPs by 75%, and latency by 45%.
  arXiv  Detail & Related papers  (2025-03-26T04:16:48Z)
• Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation [30.912818564963512]
  DETRIS is a parameter-efficient tuning framework designed to enhance low-rank visual feature propagation.<n>Our simple yet efficient approach greatly surpasses state-of-the-art methods with 0.9% to 1.8% backbone parameter updates.
  arXiv  Detail & Related papers  (2025-01-15T05:00:03Z)
• Visual Fourier Prompt Tuning [63.66866445034855]
  We propose the Visual Fourier Prompt Tuning (VFPT) method as a general and effective solution for adapting large-scale transformer-based models. Our approach incorporates the Fast Fourier Transform into prompt embeddings and harmoniously considers both spatial and frequency domain information. Our results demonstrate that our approach outperforms current state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2024-11-02T18:18:35Z)
• MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection [54.545054873239295]
  Deepfakes have recently raised significant trust issues and security concerns among the public.<n>ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance.<n>This work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach.
  arXiv  Detail & Related papers  (2024-04-12T13:02:08Z)
• Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation [67.13876021157887]
  Dynamic Tuning (DyT) is a novel approach to improve both parameter and inference efficiency for ViT adaptation. DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.
  arXiv  Detail & Related papers  (2024-03-18T14:05:52Z)
• Skip-Attention: Improving Vision Transformers by Paying Less Attention [55.47058516775423]
  Vision computation transformers (ViTs) use expensive self-attention operations in every layer. We propose SkipAt, a method to reuse self-attention from preceding layers to approximate attention at one or more subsequent layers. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS.
  arXiv  Detail & Related papers  (2023-01-05T18:59:52Z)
• AdaViT: Adaptive Tokens for Efficient Vision Transformer [91.88404546243113]
  We introduce AdaViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. AdaViT achieves this by automatically reducing the number of tokens in vision transformers that are processed in the network as inference proceeds.
  arXiv  Detail & Related papers  (2021-12-14T18:56:07Z)

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.