Deep Learning Classification With Noisy Labels
This addresses the issue of label noise in deep learning for researchers and practitioners, but it is incremental as it reviews existing works without introducing novel solutions.
The paper tackles the problem of training deep learning classifiers, specifically for face recognition, in the presence of noisy labels, which arise from errors in large-scale data collection, and reviews existing methods to manage these annotations without presenting new results or numbers.
Deep Learning systems have shown tremendous accuracy in image classification, at the cost of big image datasets. Collecting such amounts of data can lead to labelling errors in the training set. Indexing multimedia content for retrieval, classification or recommendation can involve tagging or classification based on multiple criteria. In our case, we train face recognition systems for actors identification with a closed set of identities while being exposed to a significant number of perturbators (actors unknown to our database). Face classifiers are known to be sensitive to label noise. We review recent works on how to manage noisy annotations when training deep learning classifiers, independently from our interest in face recognition.