Skip to Main content Skip to Navigation
Conference papers

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
LIS - Laboratoire d'Informatique et Systèmes
2 SIIM - Signal et Image
LIS - Laboratoire d'Informatique et Systèmes
Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02552375
Contributor : Guillaume Sanchez <>
Submitted on : Thursday, April 23, 2020 - 3:24:28 PM
Last modification on : Wednesday, June 3, 2020 - 3:50:22 AM

File

PID6437789 (1).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02552375, version 1

Collections

Citation

Guillaume Sanchez, Vincente Guis, Ricard Marxer, Frederic Bouchara. DEEP LEARNING CLASSIFICATION WITH NOISY LABELS. ICME Workshop, Jul 2020, Londres, United Kingdom. ⟨hal-02552375⟩

Share

Metrics

Record views

85

Files downloads

26