Aug 2026
Intrinsic logit-based debiasing for class-imbalanced semi-supervised learning.
Intrinsic Logit-Based Debiasing (ILBD), a robust post-hoc framework that estimates bias directly from task-relevant data without external dependencies and class priors, and effectively rectifies the classifier's bias directly from the inherent statistical patterns of the training data.
Qianying Tang, Yue Cheng, Xiao-Yu Guo et al.
· Neural Networks · 0 citations