.png){kind=icon}
返回
Exploring probability-aware parametric softmax for model calibration in image classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113488.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• 输出质心偏差被定义为观察优化特性。• 参数Softmax映射提高了CNNs的图像分类性能。• 提出了参数RMSNorm Softmax校准用于不确定性校准。
Keyword:
Output Centroid Deviation
Parametric Softmax
RMSNorm
Uncertainty Calibration
Image Classification
期刊
IF:
7.6
论文数:
1.4W
被引数:
4.5W
机构
引用论文
Large language model uncertainty proxies: discrimination and calibration for medical diagnosis and treatment大型语言模型不确定性代理：医学诊断和治疗中的区分与校准
OAAI
OAAI分享收藏
Hyperspectral remote sensing image classification based on tighter random projection with minimal intra-class variance algorithm.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Weakly supervised adversarial learning via latent space for hyperspectral target detectionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容