This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread application of network pretraining, highlighting that it is itself subject to catastrophic forgetting. Unfortunately, this issue leads to the under-exploitation of knowledge transfer during later tasks. On this ground, we propose Transfer without Forgetting (TwF), a hybrid Continual Transfer Learning approach building upon a fixed pretrained sibling network, which continuously propagates the knowledge inherent in the source domain through a layer-wise loss term. Our experiments indicate that TwF steadily outperforms other CL methods across a variety of settings, averaging a 4.81% gain in Class-Incremental accuracy over a variety of datasets and different buffer sizes.
Transfer without Forgetting / Boschini, Matteo; Bonicelli, Lorenzo; Porrello, Angelo; Bellitto, Giovanni; Pennisi, Matteo; Palazzo, Simone; Spampinato, Concetto; Calderara, Simone. - 13683 LNCS:(2022), pp. 692-709. (Intervento presentato al convegno 17th European Conference on Computer Vision, ECCV 2022 tenutosi a Tel Aviv, Israel nel 23-27 Oct, 2022) [10.1007/978-3-031-20050-2_40].
Transfer without Forgetting
Matteo Boschini;Lorenzo Bonicelli;Angelo Porrello;Simone Calderara
2022
Abstract
This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread application of network pretraining, highlighting that it is itself subject to catastrophic forgetting. Unfortunately, this issue leads to the under-exploitation of knowledge transfer during later tasks. On this ground, we propose Transfer without Forgetting (TwF), a hybrid Continual Transfer Learning approach building upon a fixed pretrained sibling network, which continuously propagates the knowledge inherent in the source domain through a layer-wise loss term. Our experiments indicate that TwF steadily outperforms other CL methods across a variety of settings, averaging a 4.81% gain in Class-Incremental accuracy over a variety of datasets and different buffer sizes.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
