Deep learning classification with noisy labels

Guillaume Sanchez (1, 2) , Vincente Guis (2) , Ricard Marxer (1) , Frederic Bouchara (2)

1 DYNI - DYNamiques de l’Information
2 SIIM - Signal et Image

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.

Mots clés: label noise; noisy training; noisy dataset; Index Terms-image classifier

Domaines: Apprentissage [cs.LG]

Guillaume Sanchez, Vincente Guis, Ricard Marxer, Frederic Bouchara. Deep learning classification with noisy labels. ICME Workshop, Jul 2020, Londres, United Kingdom. ⟨hal-02552375⟩