Analysis of classifiers robust to noisy labels
This work addresses the problem of noisy labels in classification for machine learning practitioners, but it appears incremental as it analyzes existing methods rather than introducing new ones.
The paper analyzed three robust classification algorithms (Forward, Importance Re-weighting, and T-revision) for handling class-dependent label noise, demonstrating methods to estimate transition matrices for improved performance on noisy data. It applied deep learning to three datasets, including CIFAR with unknown noise, and evaluated effectiveness using top-1 accuracy.
We explore contemporary robust classification algorithms for overcoming class-dependant labelling noise: Forward, Importance Re-weighting and T-revision. The classifiers are trained and evaluated on class-conditional random label noise data while the final test data is clean. We demonstrate methods for estimating the transition matrix in order to obtain better classifier performance when working with noisy data. We apply deep learning to three data-sets and derive an end-to-end analysis with unknown noise on the CIFAR data-set from scratch. The effectiveness and robustness of the classifiers are analysed, and we compare and contrast the results of each experiment are using top-1 accuracy as our criterion.