454 citations · 3.1k across the 117 of their papers we have counts for
25 papers · 1 filter
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Jiaheng Wei, Zhaowei Zhu, Hao Cheng +3
Existing research on learning with noisy labels mainly focuses on synthetic label noise. Synthetic noise, though has clean structures which greatly enabled statistical analyses, of…
Active Refinement for Multi-Label Learning: A Pseudo-Label Approach
Cheng-Yu Hsieh, Wei-I Lin, Miao Xu +3
The goal of multi-label learning (MLL) is to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where t…
Instance-dependent Label-noise Learning under a Structural Causal Model
Yu Yao, Tongliang Liu, Mingming Gong +3
Label noise will degenerate the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let X and Y denote the instance and clean label, r…
Local Reweighting for Adversarial Training
Ruize Gao, Feng Liu, Kaiwen Zhou +3
Instances-reweighted adversarial training (IRAT) can significantly boost the robustness of trained models, where data being less/more vulnerable to the given attack are assigned sm…
Multi-Class Classification from Single-Class Data with Confidences
Yuzhou Cao, Lei Feng, Senlin Shu +4
Can we learn a multi-class classifier from only data of a single class? We show that without any assumptions on the loss functions, models, and optimizers, we can successfully lear…
Understanding and Improving Early Stopping for Learning with Noisy Labels
Yingbin Bai, Erkun Yang, Bo Han +5
The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick,…