Combating Label Noise in Deep Learning Using Abstention

2 code implementations • 27 May 2019 • Sunil Thulasidasan, Tanmoy Bhattacharya, Jeff Bilmes, Gopinath Chennupati, Jamal Mohd-Yusof

In the case of unstructured (arbitrary) label noise, abstention during training enables the DAC to be used as an effective data cleaner by identifying samples that are likely to have label noise.

General Classification Image Classification +1

Knows When it Doesn’t Know: Deep Abstaining Classifiers

no code implementations • ICLR 2019 • Sunil Thulasidasan, Tanmoy Bhattacharya, Jeffrey Bilmes, Gopinath Chennupati, Jamal Mohd-Yusof

We introduce the deep abstaining classifier -- a deep neural network trained with a novel loss function that provides an abstention option during training.