ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks

Xinshao Wang, Yang Hua, Elyor Kodirov, David A. Clifton, Neil M. Robertson

Keywords: label correction, entropy minimisation, maximum entropy, confidence penalty, knowledge distillation, regularization, label noise

Abstract:

To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the most appealing as it exploits its own knowledge and requires no extra models. However, how to automatically decide the trust degree of a learner as training goes is not well answered in the literature? (2) Some methods penalise while the others reward low-entropy predictions, prompting us to ask which one is better?

To resolve the first issue, taking two well-accepted propositions–deep neural networks learn meaningful patterns before fitting noise (Arpit et al., 2017) and minimum entropy regularisation principle (Grandvalet & Bengio, 2006)–we propose a novel end-to-end method named ProSelfLC, which is designed according to learning time and entropy. Specifically, given a data point, we progressively increase trust in its predicted label distribution versus its annotated one if a model has been trained for enough time and the prediction is of low entropy (high confidence). For the second issue, according to ProSelfLC, we empirically prove that it is better to redefine a meaningful low-entropy status and optimise the learner toward it. This serves as a defence of entropy minimisation.

We demonstrate the effectiveness of ProSelfLC through extensive experiments in both clean and noisy settings.

One-sentence Summary: ProSelfLC is the first method to trust self knowledge progressively and adaptively. ProSelfLC redirects and promotes entropy minimisation, which is in marked contrast to recent practices of confidence penalty.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=HVVjgLPZ0