[KongchangAI]
Unverified50% confidenceFactExact time

Dice Loss和IoU Loss对前景像素的相对比例更敏感,天然缓解类别不平衡;Focal Loss通过动态降低易分类样本的权重迫使模型专注于困难像素

1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/527099
API
curl https://kongchang.com/api/v1/knowledge/claims/527099
MCP
get_claim(id=527099)