Continual Learning (CL) enables machine learning models to learn from
continuously shifting new training data in absence of data from old tasks.
Recently, pretrained vision transformers combined with prompt tuning have shown
promise for overcoming catastrophic forgetting in CL. These approaches rely on
a pool of learnable prompts which can be inefficient in sharing knowledge
across tasks leading to inferior performance. In addition, the lack of
fine-grained layer specific prompts does not allow these to fully express the
strength of the prompts for CL. We address these limitations by proposing
ConvPrompt, a novel convolutional prompt creation mechanism that maintains
layer-wise shared embeddings, enabling both layer-specific learning and better
concept transfer across tasks. The intelligent use of convolution enables us to
maintain a low parameter overhead without compromising performance. We further
leverage Large Language Models to generate fine-grained text descriptions of
each category which are used to get task similarity and dynamically decide the
number of prompts to be learned. Extensive experiments demonstrate the
superiority of ConvPrompt and improves SOTA by ~3% with significantly less
parameter overhead. We also perform strong ablation over various modules to
disentangle the importance of different components.

提出了 ConvPrompt，一种新颖的卷积提示创建机制，通过维护逐层共享的嵌入，实现了层特定学习和更好的概念传递，从而克服了 Catastrophic Forgetting 在 Continual Learning 中的问题。通过使用卷积的智能化利用，可以保持较低的参数开销而不影响性能，并通过大型语言模型生成每个类别的细粒度文本描述，用于获取任务相似性并动态决定要学习的提示数量。在广泛的实验证明了 ConvPrompt 的优越性，并显著提高了 SOTA 约 3%，参数开销更少。同时进行了强有力的模块剥离以剖析不同组成部分的重要性。