research
∙
07/31/2023
Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
Current state-of-the-art results in computer vision depend in part on fi...
research
∙
02/23/2023
Detachedly Learn a Classifier for Class-Incremental Learning
In continual learning, model needs to continually learn a feature extrac...
research
∙
12/06/2022
FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer
Recent work has explored the potential to adapt a pre-trained vision tra...
research
∙
07/14/2022
Convolutional Bypasses Are Better Vision Transformer Adapters
The pretrain-then-finetune paradigm has been widely adopted in computer ...
research
∙
05/19/2022
Bypassing Logits Bias in Online Class-Incremental Learning with a Generative Framework
Continual learning requires the model to maintain the learned knowledge ...
research
∙
04/22/2022