Prototype-Anchored Learning for Learning with Imperfect Annotations. (arXiv:2206.11602v1 [cs.LG])

The success of deep neural networks greatly relies on the availability of
large amounts of high-quality annotated data, which however are difficult or
expensive to obtain. The resulting labels may be class imbalanced, noisy or
human biased. It is challenging to learn unbiased classification models from
imperfectly annotated datasets, on which we usually suffer from overfitting or
underfitting. In this work, we thoroughly investigate the popular softmax loss
and margin-based loss, and offer a feasible approach to tighten the
generalization …

annotations arxiv learning lg