InfantFace model achieves 0.96 AP50 for infant face detection

Researchers have developed a new model called InfantFace, designed to accurately detect infant faces in challenging neonatal clinical settings. This model, based on the YOLOv11m architecture, addresses issues like cluttered backgrounds, poor lighting, and obstructions from medical equipment. After training on a combination of public datasets and fine-tuning on a specific neonatal research dataset, InfantFace achieved a high AP50 score of 0.96, significantly outperforming existing general face detectors. The study also highlights the need for more publicly available, ethically sourced neonatal datasets to further advance research in this area. AI

IMPACT This model could improve non-contact clinical assessments for infants, such as pain analysis and monitoring, by providing reliable facial detection.

RANK_REASON The cluster contains an academic paper detailing a new model and its performance on a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• Celeba
• FDDB
• Hugging Face
• InfantFace
• VGGFace2: A Dataset for Recognising Faces across Pose and Age
• WIDER FACE
• YOLOv11m

• paper
• product

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