LGMLJun 13, 2020

Generalization by Recognizing Confusion

arXiv:2006.07737v11 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses robustness to label noise for image recognition, which is an incremental improvement over existing methods.

The paper tackles the problem of improving neural network generalization and robustness to label noise by combining self-adaptive training with mixup, achieving state-of-the-art accuracies on corrupted image datasets.

A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By combining the self-adaptive objective with mixup, we further improve the accuracy of self-adaptive models for image recognition; the resulting classifier obtains state-of-the-art accuracies on datasets corrupted with label noise. Robustness to label noise implies a lower generalization gap; thus, our approach also leads to improved generalizability. We find evidence that the Rademacher complexity of these algorithms is low, suggesting a new path towards provable generalization for this type of deep learning model. Last, we highlight a novel connection between difficulties accounting for rare classes and robustness under noise, as rare classes are in a sense indistinguishable from label noise. Our code can be found at https://github.com/Tuxianeer/generalizationconfusion.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes