Forest Neural Network advances kinship verification accuracy

Researchers have developed a novel Forest Neural Network approach for kinship verification, utilizing graph neural network concepts to learn from facial images. This method achieves comparable results to algorithms that jointly represent parent and child facial images. The proposed network incorporates a specific classification module design and a combined loss function that gradually integrates center loss during training. Experiments conducted on the KinFaceW-I and KinFaceW-II datasets demonstrated the effectiveness of this approach, achieving top performance on KinFaceW-II with an average improvement of 1.6 across kinship types and near-best results on KinFaceW-I. AI

IMPACT This research introduces a novel neural network architecture for kinship verification, potentially improving accuracy in facial recognition tasks.

RANK_REASON The cluster contains a research paper detailing a new model architecture for a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Ali Nazari
• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Forest Neural Network
• Gotit.pub
• Hugging Face
• KinFaceW-I
• KinFaceW-II
• ScienceCast

• paper
• other

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