Vision Transformers enhanced with registers for better face recognition

Researchers have developed a new method using register tokens to improve the interpretability and performance of Vision Transformers (ViTs) for face recognition. By adding learnable register tokens to the input embeddings, the model produces more structured and understandable attention maps. This approach, particularly with eight registers, significantly enhances verification accuracy and has achieved state-of-the-art results on large-scale benchmarks like IJB-B and IJB-C. AI

IMPACT Introduces a novel technique to enhance the interpretability and accuracy of ViTs for face recognition tasks.

RANK_REASON The cluster contains an academic paper detailing a new method for improving existing models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• face recognition
• IJB-B
• IJB-C
• register tokens
• Vision Transformers

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →