Back to Search Start Over

On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers

Authors :
De Min, Thomas
Mancini, Massimiliano
Alahari, Karteek
Alameda-Pineda, Xavier
Ricci, Elisa
Publication Year :
2023

Abstract

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of learned parameters and the performance, making such models computationally expensive. In this work, we aim to reduce this cost while maintaining competitive performance. We achieve this by revisiting and extending a simple transfer learning idea: learning task-specific normalization layers. Specifically, we tune the scale and bias parameters of LayerNorm for each continual learning task, selecting them at inference time based on the similarity between task-specific keys and the output of the pre-trained model. To make the classifier robust to incorrect selection of parameters during inference, we introduce a two-stage training procedure, where we first optimize the task-specific parameters and then train the classifier with the same selection procedure of the inference time. Experiments on ImageNet-R and CIFAR-100 show that our method achieves results that are either superior or on par with {the state of the art} while being computationally cheaper.<br />Comment: In The First Workshop on Visual Continual Learning (ICCVW 2023); Oral

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2308.09610
Document Type :
Working Paper