返回
Intrinsic logit-based debiasing for class-imbalanced semi-supervised learning
DOI:10.1016/j.neunet.2026.109533.png)
摘要
En 中文
无标签固有偏差估计通过K-1非目标logits的平均值。
标签引导学习偏差估计通过目标类logits的平均值。
在多个数据集和CISSL设置上超越最先进方法。
Keyword:
Semi-supervised learning
Class-imbalanced learning
Logit adjustment
Long-tailed recognition
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
GQEO: Nearest neighbor graph-based generalized quadrilateral element oversampling for class-imbalance problem
NEURAL NETWORKS
IF6.3
Loyalty-SMOTE: Data Synthesis Algorithm for Effective Imbalanced Data Classification忠诚度-SMOTE: 有效的不平衡数据分类的数据合成算法
Neural Networks
IF6.3
EKDSC: Long-tailed recognition based on expert knowledge distillation for specific categoriesEKDSC: 基于专家知识蒸馏的特定类别长尾识别
Neural Networks
IF6.3
FGBC: Flexible graph-based balanced classifier for class-imbalanced semi-supervised learningFGBC: 用于类不平衡半监督学习的灵活的基于图的平衡分类器
PATTERN RECOGNITION
IF7.6
DCRP: Class-Aware Feature Diffusion Constraint and Reliable Pseudo-Labeling for Imbalanced Semi-Supervised LearningDCRP: 不平衡半监督学习的类感知特征扩散约束和可靠伪标记
Diverse Teacher-Students for deep safe semi-supervised learning under class mismatch类不匹配下用于深度安全半监督学习的多样化教师-学生
NEURAL NETWORKS
IF6.3
SemiDDM-weather: A semi-supervised learning framework for all-in-one adverse weather removalSemiDDM-weather:一种用于全流程恶劣天气去除的半监督学习框架
Neural Networks
IF6.3
没有更多内容

