
A novel continual learning approach that automatically expands pre-trained vision transformers by adding modular adapters and representation descriptors to accommodate distribution shifts in incoming tasks, without the need for memory rehearsal.


coremsg

automated-expansion-of-pre-trained-vision-transformers-for-continual-learning


Automated Expansion of Pre-trained Vision Transformers for Continual Learning


title_rewrite


The core message of this paper is that incrementally tuning the shared adapter without imposing parameter update constraints is an effective continual learning strategy for pre-trained vision transformers, and further performance improvements can be achieved by retraining a unified classifier with semantic shift-compensated prototypes.


semantically-shifted-incremental-adapter-tuning-a-continual-learning-framework-for-vitransformers


Semantically-Shifted Incremental Adapter-Tuning: A Continual Learning Framework for ViTransformers
