← Back to all news
arXiv Computer Vision By Guray Ozgur, Mustafa Efe Tamyapar, Naser Damer, Fadi Boutros

EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment

Read the original on arXiv Computer Vision →

EXPL-FR is a lightweight adapter that aligns a vision‑language model’s image encoder with a frozen face‑recognition (FR) embedding space, enabling the FR model to be explained using semantic attribute prompts without any text training. By mapping 978 attribute prompts across 22 categories into the FR space, the method identifies the most detectable concepts—forming a readable semantic signature that better separates identities than the full vocabulary. The approach is evaluated on four FR backbones and two VLM encoders, providing identity‑level, per‑image, and differential explanations, and demonstrates that prompt‑driven audits can rank FR models by per‑ethnicity error and attribute‑change verification cost without requiring labeled data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Sep 21

Benchmarking the Explanatory Quality of Open-Weight Vision-Language Models in Face Recognition

The paper introduces a benchmarking framework that evaluates open-weight Vision‑Language Models (VLMs) for face recognition by treating explanation quality as a core metric. It defines two key criteria for explanations—relevance, meaning reliance on identity‑stable facial features, and faithfulness, meaning alignment with the visible image content without hallucinations. Using this framework, the authors benchmark several VLM families, jointly assessing face verification accuracy and explanation quality, and find that current models still exhibit shortcomings in their explanations, underscoring the importance of explanation metrics for a complete performance assessment.

By Laurent Colbois, S\'ebastien Marcel
llmsfine-tuningmultimodalbenchmarkssafety
More like this →
arXiv AI
Jun 4

CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systems

arXiv:2407. 13922v3 Announce Type: replace-cross Abstract: Face recognition (FR) systems are widely deployed in critical applications, making their reliability and robustness across diverse populations and conditions essential.

By Guruprasad Viswanathan Ramesh, Ashish Hooda, Shimaa Ahmed, Harrison J Rosenberg, Ramya Korlakai Vinayak, Kassem Fawaz
benchmarks
More like this →