CATFace: Cross-Attribute-Guided Transformer with Self-Attention Distillation for Low-Quality Face Recognition

• URL: http://arxiv.org/abs/2401.03037v1
• Date: Fri, 5 Jan 2024 19:21:31 GMT
• Title: CATFace: Cross-Attribute-Guided Transformer with Self-Attention Distillation for Low-Quality Face Recognition
• Authors: Niloufar Alipour Talemi, Hossein Kashiani, and Nasser M. Nasrabadi
• Abstract summary: We propose a novel multi-branch neural network that leverages soft biometric (SB) attribute information to boost the performance of face recognition (FR) We introduce a novel self-attention distillation framework that effectively highlights crucial facial regions, such as landmarks by aligning low-quality images with those of their high-quality counterparts in the feature space.
• Score: 12.129404936688752
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although face recognition (FR) has achieved great success in recent years, it is still challenging to accurately recognize faces in low-quality images due to the obscured facial details. Nevertheless, it is often feasible to make predictions about specific soft biometric (SB) attributes, such as gender, and baldness even in dealing with low-quality images. In this paper, we propose a novel multi-branch neural network that leverages SB attribute information to boost the performance of FR. To this end, we propose a cross-attribute-guided transformer fusion (CATF) module that effectively captures the long-range dependencies and relationships between FR and SB feature representations. The synergy created by the reciprocal flow of information in the dual cross-attention operations of the proposed CATF module enhances the performance of FR. Furthermore, we introduce a novel self-attention distillation framework that effectively highlights crucial facial regions, such as landmarks by aligning low-quality images with those of their high-quality counterparts in the feature space. The proposed self-attention distillation regularizes our network to learn a unified quality-invariant feature representation in unconstrained environments. We conduct extensive experiments on various FR benchmarks varying in quality. Experimental results demonstrate the superiority of our FR method compared to state-of-the-art FR studies.

Related papers

• ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition [16.40653529334528]
  We propose a method that considers Face Alignment Errors (FAE) as another quality factor that is tailored to Face Recognition (FR) We formalize the problem as a combination of differentiable spatial transformations and adversarial data augmentation in FR. We demonstrate the benefits of the proposed method by conducting evaluations on IJB-B, IJB-C, IJB-S and TinyFace.
  arXiv  Detail & Related papers  (2024-07-20T19:58:41Z)
• DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation [84.0586749616249]
  This paper presents DiffFAE, a one-stage and highly-efficient diffusion-based framework tailored for high-fidelity Facial Appearance Editing. For high-fidelity query attributes transfer, we adopt Space-sensitive Physical Customization (SPC), which ensures the fidelity and generalization ability. In order to preserve source attributes, we introduce the Region-responsive Semantic Composition (RSC) This module is guided to learn decoupled source-regarding features, thereby better preserving the identity and alleviating artifacts from non-facial attributes such as hair, clothes, and background.
  arXiv  Detail & Related papers  (2024-03-26T12:53:10Z)
• Text-Guided Face Recognition using Multi-Granularity Cross-Modal Contrastive Learning [0.0]
  We introduce text-guided face recognition (TGFR) to analyze the impact of integrating facial attributes in the form of natural language descriptions. TGFR demonstrates remarkable improvements, particularly on low-quality images, over existing face recognition models.
  arXiv  Detail & Related papers  (2023-12-14T22:04:22Z)
• TransFA: Transformer-based Representation for Face Attribute Evaluation [87.09529826340304]
  We propose a novel textbftransformer-based representation for textbfattribute evaluation method (textbfTransFA) The proposed TransFA achieves superior performances compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-07-12T10:58:06Z)
• Learning Transformer Features for Image Quality Assessment [53.51379676690971]
  We propose a unified IQA framework that utilizes CNN backbone and transformer encoder to extract features. The proposed framework is compatible with both FR and NR modes and allows for a joint training scheme.
  arXiv  Detail & Related papers  (2021-12-01T13:23:00Z)
• Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment [26.792481400792376]
  In many face recognition (FR) scenarios, face images are acquired from a sequence with huge intra-variations. We present an efficient non-reference image quality assessment for FR that directly links image quality assessment (IQA) and FR. Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data.
  arXiv  Detail & Related papers  (2021-06-09T07:20:54Z)
• 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)
• A Comprehensive Study on Face Recognition Biases Beyond Demographics [12.18029358410109]
  Face recognition (FR) systems have a growing effect on critical decision-making processes. Recent works have shown that FR solutions show strong performance differences based on the user's demographics. To enable a trustworthy FR technology, it is essential to know the influence of an extended range of facial attributes on FR.
  arXiv  Detail & Related papers  (2021-03-02T09:29:09Z)
• Unpaired Image Enhancement with Quality-Attention Generative Adversarial Network [92.01145655155374]
  We propose a quality attention generative adversarial network (QAGAN) trained on unpaired data. Key novelty of the proposed QAGAN lies in the injected QAM for the generator. Our proposed method achieves better performance in both objective and subjective evaluations.
  arXiv  Detail & Related papers  (2020-12-30T05:57:20Z)
• Face Anti-Spoofing Via Disentangled Representation Learning [90.90512800361742]
  Face anti-spoofing is crucial to security of face recognition systems. We propose a novel perspective of face anti-spoofing that disentangles the liveness features and content features from images.
  arXiv  Detail & Related papers  (2020-08-19T03:54:23Z)

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.