The proposed Soft-label Refurbishment with Ensemble Learning (SoREL), a two-stage framework that jointly handles label noise and class imbalance, and refurbished soft labels guide multi-expert ensemble learning, where experts specialize in many, medium, and few-shot classes.
This article utilizes bias-variance-diversity (BVD) decomposition theory to examine the impact of noisy labels on three mainstream ensemble paradigms: Bagging, Boosting, and Stacking and characterizes the mechanisms behind performance degradation.
Guanxiong He, Jie Wang, Zhiyong Li et al.· IEEE Transactions on Neural...· 1 citation
This work proposes a class coverage-aware noise correction method for crowdsourced labels via elimination-based inference (COVER-EL), and provides a probably approximately correct (PAC)-style bound that gives a high-probability guarantee on the overall error after correction.
Bi Wang, Yan-Ting Yang, Xuelian Li· IEEE Transactions on Neural...· 0 citations
This paper proposes a novel Partial label-based Self-training framework (PaSta) that leverages partial label learning technique to overcome the limitations of existing methods and designs a partial label-based classification model with two well-crafted loss functions to guide the model learning at both label and repres...
Yu-Jing Liu, Yi-Xin Liu, Yu Zheng et al.· 0 citations
While SSL outperforms training from scratch on average and remains competitive with state-of-the-art tree ensembles, the SSL-vs-scratch gains exhibit high inter-task variance and lack significance, indicating the findings reflect general properties of tabular SSL rather than idiosyncrasies of one particular pretext tas...
This work conducts a comparative empirical study of five MU methods across symmetric, asymmetric, instance-dependent, and open-set noise on CIFAR-10, CIFAR-100, and the real-world noisy dataset Food-101N and finds that the appropriate unlearning strategy is conditioned on the noise structure.
Experimental results on CIFAR-10, CIFAR-100, Animal-10N, and Mini-WebVision, together with additional evaluation under open-set noise, show that the proposed CANNE method achieves competitive performance across diverse noisy-label settings.
Ge Jin, Qian Zhang, Li Huang et al.· Entropy· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
