Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning
This addresses the challenge of continual learning with few samples for AI systems, though it appears incremental as it builds on existing FSCIL methods by incorporating text information.
The paper tackles the problem of few-shot class-incremental learning (FSCIL), where models must learn new tasks from limited data without forgetting old ones, by proposing a method that leverages label-text information with a memory prompt and stimulation-based training, resulting in outperforming prior state-of-the-art approaches and significantly mitigating catastrophic forgetting and overfitting.
Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old ones. The difficulties are that training on a sequence of limited data from new tasks leads to severe overfitting issues and causes the well-known catastrophic forgetting problem. Existing researches mainly utilize the image information, such as storing the image knowledge of previous tasks or limiting classifiers updating. However, they ignore analyzing the informative and less noisy text information of class labels. In this work, we propose leveraging the label-text information by adopting the memory prompt. The memory prompt can learn new data sequentially, and meanwhile store the previous knowledge. Furthermore, to optimize the memory prompt without undermining the stored knowledge, we propose a stimulation-based training strategy. It optimizes the memory prompt depending on the image embedding stimulation, which is the distribution of the image embedding elements. Experiments show that our proposed method outperforms all prior state-of-the-art approaches, significantly mitigating the catastrophic forgetting and overfitting problems.