Learning to Combat Noisy Labels via Classification Margins
This addresses the issue of noisy labels in deep learning, which is crucial for real-world applications where data is often imperfect, but it is an incremental improvement over existing robust learning methods.
The paper tackles the problem of deep neural networks memorizing noisy labels, which degrades generalization, by proposing MARVEL, a method that identifies and abandons noisy instances based on classification margin history. Experimental results show MARVEL consistently outperforms baselines across noise levels, with a significantly larger margin under asymmetric noise.
A deep neural network trained on noisy labels is known to quickly lose its power to discriminate clean instances from noisy ones. After the early learning phase has ended, the network memorizes the noisy instances, which leads to a significant degradation in its generalization performance. To resolve this issue, we propose MARVEL (MARgins Via Early Learning), a new robust learning method where the memorization of the noisy instances is curbed. We propose a new test statistic that tracks the goodness of "fit" of every instance based on the epoch-history of its classification margins. If its classification margin is small in a sequence of consecutive learning epochs, that instance is declared noisy and the network abandons learning on it. Consequently, the network first flags a possibly noisy instance, and then waits to see if learning on that instance can be improved and if not, the network learns with confidence that this instance can be safely abandoned. We also propose MARVEL+, where arduous instances can be upweighted, enabling the network to focus and improve its learning on them and consequently its generalization. Experimental results on benchmark datasets with synthetic label noise and real-world datasets show that MARVEL outperforms other baselines consistently across different noise levels, with a significantly larger margin under asymmetric noise.