Multimodal Parameter-Efficient Few-Shot Class Incremental Learning

Abstract

Few-Shot Class Incremental Learning (FSCIL) is a challenging continual learning task, where limited training examples are available during several learning sessions. To succeed in this task, it is necessary to avoid over-fitting new classes caused by biased distributions in the few-shot training sets. The general approach to address this issue involves enhancing the representational capability of a pre-defined backbone architecture by adding special modules for backward compatibility with older classes. However, this approach has not yet solved the dilemma of ensuring high classification accuracy over time while reducing the gap between the performance obtained on larger training sets and the smaller ones. In this work, we propose an alternative approach called Continual Parameter-Efficient CLIP (CPE-CLIP) to reduce the loss of information between different learning sessions. Instead of adapting additional modules to address information loss, we leverage the vast knowledge acquired by CLIP in large-scale pre-training and its effectiveness in generalizing to new concepts. Our approach is multimodal and parameter-efficient, relying on learnable prompts for both the language and vision encoders to enable transfer learning across sessions. We also introduce prompt regularization to improve performance and prevent forgetting. Our experimental results demonstrate that CPE-CLIP significantly improves FSCIL performance compared to state-of-the-art proposals while also drastically reducing the number of learnable parameters and training costs.

References in corpus (11)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Learning to Prompt for Vision-Language Models
• Towards a Unified View of Parameter-Efficient Transfer Learning
• K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
• DualNet: Continual Learning, Fast and Slow
• Recent Advances of Continual Learning in Computer Vision: An Overview
• Tell me what this is: Few-Shot Incremental Object Learning by a Robot
• Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
• Progressive Prompts: Continual Learning for Language Models
• CLIP model is an Efficient Continual Learner
• HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks