<ul data-eligibleForWebStory="true"><li>A new method called Dual Prototype network for Task-wise Adaption (DPTA) is proposed for Class-Incremental Learning (CIL) using pre-trained models (PTM).</li><li>DPTA aims to address the challenge of catastrophic forgetting when fine-tuning PTMs on downstream incremental tasks by introducing adapter modules for each task to improve model adaption.</li><li>The DPTA method utilizes dual prototypes to enhance the prediction process by enabling test-time adapter selection and utilizing augmented prototypes to improve class separability.</li><li>Experiments on benchmark datasets have shown that DPTA outperforms existing methods in CIL, and the code for DPTA is available on GitHub for further exploration.</li></ul>

Integrating Dual Prototypes for Task-Wise Adaption in Pre-Trained Model-Based Class-Incremental Learning

Discover more