Unverified85% confidenceBenchmarkExact time
ArcFace proposed the Additive Angular Margin Loss in 2018, achieving over 99.8% recognition accuracy on standard benchmarks like LFW
1
Sources
85%
Confidence
Long-term
Relevance
8/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedArcFace由2019年邓建康等人提出，采用加性角度间隔损失77% similarUnverifiedArcFace是专为人脸识别优化的深度度量学习方法，通过引入加性角度间隔损失函数，在人脸身份特征提取精度上优于通用视觉编码器70% similarUnverifiedESRGAN引入了感知损失（Perceptual Loss）和残差密集块（RRDB），在超分辨率上效果显著56% similarUnverifiedoutline支持outline-offset属性，可以设置负值让轮廓向内收缩51% similarUnverified支持无感自动对焦、自动梯形校正和智能避障，适合不想折腾安装调试的用户；但侧投大角度校正会损失分辨率，追求最佳4K画质建议正投50% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/680476API
curl https://kongchang.com/api/v1/knowledge/claims/680476MCP
get_claim(id=680476)