End-to-End Incremental Learning
In: ECCV 2018 - European Conference on Computer Vision ; https://inria.hal.science/hal-01849366 ; ECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.241-257, ⟨10.1007/978-3-030-01258-8_15⟩, 2018
Online
Konferenz
Zugriff:
International audience ; Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added incrementally. This is due to current neural network architectures requiring the entire dataset, consisting of all the samples from the old as well as the new classes, to update the model---a requirement that becomes easily unsustainable as the number of classes grows. We address this issue with our approach to learn deep neural networks incrementally, using new data and only a small exemplar set corresponding to samples from the old classes. This is based on a loss composed of a distillation measure to retain the knowledge acquired from the old classes, and a cross-entropy loss to learn the new classes. Our incremental training is achieved while keeping the entire framework end-to-end, i.e., learning the data representation and the classifier jointly, unlike recent methods with no such guarantees. We evaluate our method extensively on the CIFAR-100 and ImageNet (ILSVRC 2012) image classification datasets, and show state-of-the-art performance.
Titel: |
End-to-End Incremental Learning
|
---|---|
Autor/in / Beteiligte Person: | Castro, Francisco, M. ; Marín-Jiménez, Manuel, J ; Guil, Nicolás ; Schmid, Cordelia ; Alahari, Karteek ; Departamento Lenguajes y Ciencias de la Computación (LCC) ; Universidad de Málaga Málaga = University of Málaga Málaga ; Universidad de Córdoba = University of Córdoba Córdoba ; Apprentissage de modèles à partir de données massives (Thoth ) ; Inria Grenoble - Rhône-Alpes ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK ) ; Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes 2016-2019 (UGA 2016-2019 )-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes 2016-2019 (UGA 2016-2019 ) ; Ferrari, Vittorio ; Hebert, Martial ; Sminchisescu, Cristian ; Weiss, Yair ; ERC_Allegro ; CEFIPRA_Everest ; European Project: 320559,EC:FP7:ERC,ERC-2012-ADG_20120216,ALLEGRO(2013) |
Link: | |
Zeitschrift: | ECCV 2018 - European Conference on Computer Vision ; https://inria.hal.science/hal-01849366 ; ECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.241-257, ⟨10.1007/978-3-030-01258-8_15⟩, 2018 |
Veröffentlichung: | HAL CCSD ; Springer, 2018 |
Medientyp: | Konferenz |
DOI: | 10.1007/978-3-030-01258-8_15 |
Schlagwort: |
|
Sonstiges: |
|