SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels. (arXiv:2211.11753v1 [cs.LG] CROSS LISTED)

Annotating the dataset with high-quality labels is crucial for performance of
deep network, but in real world scenarios, the labels are often contaminated by
noise. To address this, some methods were proposed to automatically split clean
and noisy labels, and learn a semi-supervised learner in a Learning with Noisy
Labels (LNL) framework. However, they leverage a handcrafted module for
clean-noisy label splitting, which induces a confirmation bias in the
semi-supervised learning phase and limits the performance. In this paper, we …

arxiv labels