EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment
FraunhoferIGD · hf · 2026-08-25
Fraunhofer IGD released EXPL-FR, which explains face recognition similarity scores by aligning vision-language embeddings to the recognition space. It enables label-free auditing of semantic attributes and model comparison.
More from Research
- AutoScientist extends to auto-configuring reinforcement learning recipes — sarahookr · 2026-08-25
- Marin: Open-source framework for foundation model R&D — marin-community · 2026-08-25
- Hamming's Three Questions: Why Aren't You Working on the Most Important Problem? — IgorCarron · 2026-08-25
- AR Visualization Cuts Teleoperation Time by 24% via Impedance Control — rsasaki0109 · 2026-08-25
- AI Grinding Paper: Agents Automatically Break 8 Cryptographic Schemes — matthew_d_green · 2026-08-25
- Papers with Code Search Engine: Powered by Hugging Face Infrastructure — NielsRogge · 2026-08-25