TY - JOUR
T1 - Visual Prompt Tuning in Null Space for Continual Learning
AU - Lu, Yue
AU - Zhang, Shizhou
AU - Cheng, De
AU - Xing, Yinghui
AU - Wang, Nannan
AU - Wang, Peng
AU - Zhang, Yanning
N1 - Publisher Copyright:
© 2024 Neural information processing systems foundation. All rights reserved.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=105000497728&partnerID=8YFLogxK
M3 - 会议文章
AN - SCOPUS:105000497728
SN - 1049-5258
VL - 37
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 38th Conference on Neural Information Processing Systems, NeurIPS 2024
Y2 - 9 December 2024 through 15 December 2024
ER -