The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
arXiv:2610.27728v1 Announce Type: new Abstract: Real-world datasets are inherently class-imbalanced, leading models to favor majority classes and struggle with minority ones. Existing logit adjustmen...
arXiv:2604. 02765v2 Announce Type: replace Abstract: Class-incremental learning (CIL) is commonly evaluated under predefined schedules with fixed or nearly equal class increments, leaving irregular class-arrival scenarios underexplored.
arXiv:2610.27443v1 Announce Type: new Abstract: Set-valued classification (SVC) offers a practical approach to communicating uncertainty while maintaining accuracy by predicting variable-sized sets p...
arXiv:2608.30699v1 Announce Type: cross Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...
arXiv:2602. 17853v2 Announce Type: replace Abstract: Logit adjustment corrects class imbalance using the empirical class prior.
arXiv:2609.16380v1 Announce Type: new Abstract: Class-balanced learning and label noise create a coupled failure mode: frequency correction prevents majority classes from dominating the decision rule...