most citedIPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

2 citations · 2 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2025

Best Transition Matrix Esitimation or Best Label Noise Robustness Classifier? Two Possible Methods to Enhance the Performance of T-revision

Haixu Liu, Zerui Tao, Naihui Zhang +1

Label noise refers to incorrect labels in a dataset caused by human errors or collection defects, which is common in real-world applications and can significantly reduce the accura…

cs.CV2023★ 2 cited

IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

Zhenglin Huang, Xiaoan Bao, Na Zhang +4

Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in…