Unverified50% confidenceDecision RuleExact time
如果交叉熵稳步下降而Dice波动剧烈，问题几乎可以确定出在Dice损失的配置上
1
Sources
50%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
Related Claims
VerifiedCross-entropy loss originates from KL divergence in information theory and measures the degree of difference between the true probability distribution and the predicted probability distribution.74% similarUnverified标准交叉熵损失在目标占图像面积较小时会导致严重的类别不平衡问题，模型倾向于全部预测为背景72% similarUnverifiedCross-entropy loss often converges faster than MSE in classification tasks because, when paired with softmax output, gradients do not vanish in the saturation region.70% similarUnverified逻辑回归中的交叉熵损失如果直接对 log(0) 求值会产生负无穷，需要加入极小的 epsilon 值或使用 log-sum-exp 技巧69% similarUnverifiedSanturkar等人2018年的研究指出BN的真正作用可能在于平滑损失曲面而非减少内部协变量偏移69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/692752API
curl https://kongchang.com/api/v1/knowledge/claims/692752MCP
get_claim(id=692752)