Visual Prompt Tuning in Null Space for Continual Learning

Yue Lu, Shizhou Zhang, De Cheng, Yinghui Xing, Nannan Wang, Peng Wang, Yanning Zhang

科研成果: 期刊稿件会议文章同行评审

4 引用 (Scopus)

摘要

Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On the contrary, this paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features, so as to ensure no interference on tasks that have been learned to overcome catastrophic forgetting in CL. However, different from the orthogonal projection in the traditional CNN architecture, the prompt gradient orthogonal projection in the ViT architecture shows completely different and greater challenges, i.e., 1) the high-order and non-linear self-attention operation; 2) the drift of prompt distribution brought by the LayerNorm in the transformer block. Theoretically, we have finally deduced two consistency conditions to achieve the prompt gradient orthogonal projection, which provide a theoretical guarantee of eliminating interference on previously learned knowledge via the self-attention mechanism in visual prompt tuning. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient orthogonal projection. Extensive experimental results demonstrate the effectiveness of anti-forgetting on four class-incremental benchmarks with diverse pre-trained baseline models, and our approach achieves superior performances to state-of-the-art methods. Our code is available at https://github.com/zugexiaodui/VPTinNSforCL.

源语言英语
期刊Advances in Neural Information Processing Systems
37
出版状态已出版 - 2024
活动38th Conference on Neural Information Processing Systems, NeurIPS 2024 - Vancouver, 加拿大
期限: 9 12月 202415 12月 2024

指纹

探究 'Visual Prompt Tuning in Null Space for Continual Learning' 的科研主题。它们共同构成独一无二的指纹。

引用此