Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AHAN: Asymmetric Hierarchical Attention Network for Identical Twin Face Verification

Hoang-Nhat Nguyen

TL;DR

The Asymmetric Hierarchical Attention Network (AHAN) is proposed, a novel architecture specifically designed for this challenge through multi-granularity facial analysis and introduces Twin-Aware Pair-Wise Cross-Attention (TA-PWCA), a training-only regularization strategy that uses each subject's own twin as the hardest possible distractor.

Abstract

Identical twin face verification represents an extreme fine-grained recognition challenge where even state-of-the-art systems fail due to overwhelming genetic similarity. Current face recognition methods achieve over 99.8% accuracy on standard benchmarks but drop dramatically to 88.9% when distinguishing identical twins, exposing critical vulnerabilities in biometric security systems. The difficulty lies in learning features that capture subtle, non-genetic variations that uniquely identify individuals. We propose the Asymmetric Hierarchical Attention Network (AHAN), a novel architecture specifically designed for this challenge through multi-granularity facial analysis. AHAN introduces a Hierarchical Cross-Attention (HCA) module that performs multi-scale analysis on semantic facial regions, enabling specialized processing at optimal resolutions. We further propose a Facial Asymmetry Attention Module (FAAM) that learns unique biometric signatures by computing cross-attention between left and right facial halves, capturing subtle asymmetric patterns that differ even between twins. To ensure the network learns truly individuating features, we introduce Twin-Aware Pair-Wise Cross-Attention (TA-PWCA), a training-only regularization strategy that uses each subject's own twin as the hardest possible distractor. Extensive experiments on the ND_TWIN dataset demonstrate that AHAN achieves 92.3% twin verification accuracy, representing a 3.4% improvement over state-of-the-art methods.

AHAN: Asymmetric Hierarchical Attention Network for Identical Twin Face Verification

TL;DR

The Asymmetric Hierarchical Attention Network (AHAN) is proposed, a novel architecture specifically designed for this challenge through multi-granularity facial analysis and introduces Twin-Aware Pair-Wise Cross-Attention (TA-PWCA), a training-only regularization strategy that uses each subject's own twin as the hardest possible distractor.

Abstract

Identical twin face verification represents an extreme fine-grained recognition challenge where even state-of-the-art systems fail due to overwhelming genetic similarity. Current face recognition methods achieve over 99.8% accuracy on standard benchmarks but drop dramatically to 88.9% when distinguishing identical twins, exposing critical vulnerabilities in biometric security systems. The difficulty lies in learning features that capture subtle, non-genetic variations that uniquely identify individuals. We propose the Asymmetric Hierarchical Attention Network (AHAN), a novel architecture specifically designed for this challenge through multi-granularity facial analysis. AHAN introduces a Hierarchical Cross-Attention (HCA) module that performs multi-scale analysis on semantic facial regions, enabling specialized processing at optimal resolutions. We further propose a Facial Asymmetry Attention Module (FAAM) that learns unique biometric signatures by computing cross-attention between left and right facial halves, capturing subtle asymmetric patterns that differ even between twins. To ensure the network learns truly individuating features, we introduce Twin-Aware Pair-Wise Cross-Attention (TA-PWCA), a training-only regularization strategy that uses each subject's own twin as the hardest possible distractor. Extensive experiments on the ND_TWIN dataset demonstrate that AHAN achieves 92.3% twin verification accuracy, representing a 3.4% improvement over state-of-the-art methods.
Paper Structure (20 sections, 13 equations, 2 figures, 4 tables)

This paper contains 20 sections, 13 equations, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Highly Similar Faces Recognition
  4. Fine-Grained Visual Categorization
  5. Proposed Approach
  6. Overview
  7. Revisiting Self-Attention for Face Recognition
  8. Hierarchical Cross-Attention (HCA) for Part-Based Analysis
  9. Facial Asymmetry Attention Module (FAAM)
  10. Twin-Aware Pair-Wise Cross-Attention (TA-PWCA)
  11. Multi-Granularity Feature Fusion and Loss Functions
  12. Experiments
  13. Dataset and Metrics
  14. Implementation Details
  15. Baselines
  16. ...and 5 more sections

Figures (2)

  • Figure 1: Visualization of the generated attention map.
  • Figure 2: Overview of the AHAN architecture. The model processes face images through a Vision Transformer dosovitskiy2020image backbone and three parallel streams: (1) Global Self-Attention for holistic features, (2) Hierarchical Cross-Attention (HCA) for multi-scale region analysis, and (3) Facial Asymmetry Attention Module (FAAM) for asymmetry signatures. Twin-Aware Pair-Wise Cross-Attention (TA-PWCA) uses the subject's twin as a distractor during training only.