Domain Incremental Learning (DIL) aims to learn from non-stationary data streams across domains while retaining and utilizing past knowledge. Although prompt-based methods effectively store multi-domain knowledge in prompt parameters and obtain advanced performance through cross-domain prompt fusion, we reveal an intrinsic limitation: component-wise misalignment between domain-specific prompts leads to conflicting knowledge integration and degraded predictions. This arises from the random positioning of knowledge components within prompts, where irrelevant component fusion introduces interference.To address this, we propose Componential Prompt-Knowledge Alignment (KA-Prompt), a novel prompt-based DIL method that introduces component-aware prompt-knowledge alignment during training, significantly improving both the learning and inference capacity of the model. KA-Prompt operates in two phases: (1) Initial Componential Structure Configuring, where a set of old prompts containing knowledge relevant to the new domain are mined via greedy search, which is then exploited to initialize new prompts to achieve reusable knowledge transfer and establish intrinsic alignment between new and old prompts. (2) Online Alignment Preservation, which dynamically identifies the target old prompts and applies adaptive componential consistency constraints as new prompts evolve. Extensive experiments on DIL benchmarks demonstrate the effectiveness of our KA-Prompt. Our source code is available at https://github.com/zhoujiahuan1991/ICML2025-KA-Prompt
Remind of the Past: Incremental Learning with Analogical Prompts
Chinese Academy of Science(中国科学院);Harbin Institute of Technology(哈尔滨工业大学);Peng Cheng Laboratory(鹏城实验室);Xi’an Jiaotong University(西安交通大学);Jinan University(暨南大学)
LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning
School of Information and Communication Engineering, BUPT(北京邮电大学信息与通信工程学院);Engineering Research Center for Information Network, Ministry of Education(教育部信息网络工程研究中心)
Not Just Object, But State: Compositional Incremental Learning without Forgetting
International School of Information Science & Engineering, Dalian University of Technology(大连理工大学信息科学与工程国际学院);MAIS&CRIPAC, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
When Prompt-based Incremental Learning Does Not Meet Strong Pretraining
Sun Yat-sen University(中山大学);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education(教育部机器智能与先进计算重点实验室);Peng Cheng Laboratory(鹏城实验室)
DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP
School of Automation, Southeast University, China(东南大学自动化学院);University of the Chinese Academy of Sciences, China(中国科学院大学);Suzhou University of Science and Technology, China(苏州科技大学);Computer Vision Center, Spain(西班牙计算机视觉中心)
DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning
Department of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术系);Research Center for Frontier Fundamental Studies, Zhejiang Lab(浙江实验室前沿基础研究中心);Department of Neurology, University of California, Irvine(加州大学伊市医学院神经科)
Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning
Institute of Trustworthy Embodied AI(可信具身人工智能研究院);Fudan University(复旦大学);Shanghai Collaborative Innovation Center of Intelligent Visual Computing(上海智能视觉计算协同创新中心);APUS AI Lab(APUS人工智能实验室)
PrePrompt: Predictive prompting for class incremental learning
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Department of Mathematics and Statistics, Beijing Technology and Business University(北京科技商务大学数学与统计学系);College of Science, Shantou University(汕头大学科学学院)
Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors
School of Computer Science and Engineering, University of New South Wales(新南威尔士大学计算机科学与工程学院);Data61, CSIRO(CSIRO数据61研究中心);School of Computer Science, University of Auckland(奥克兰大学计算机科学学院);Australian Institute for Machine Learning (AIML), The University of Adelaide(阿德莱德大学澳大利亚机器学习研究所)
Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning
Yale University(耶鲁大学);Johns Hopkins University(约翰霍普金斯大学);University of Freiburg(弗赖堡大学);Max Planck Institute for Informatics(马克斯·普朗克信息研究所);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
I3DOD: Towards Incremental 3D Object Detection via Prompting
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences(中国科学院沈阳自动化研究所机器人学国家重点实验室);Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences(中国科学院机器人与智能制造研究所);University of Chinese Academy of Sciences(中国科学院大学);Institute of Microsystem and Information Technology, Chinese Academy of Sciences(中国科学院微系统与信息技术研究所)
Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning
University of Trento(特伦托大学);LTCI, Télécom Paris(法国巴黎高等电信学院LTCI实验室);Institut Polytechnique de Paris(巴黎理工学院);University of Aberdeen(阿伯丁大学);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会)
Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning
University of Chinese Academy of Sciences(中国科学院大学);Peking University(北京大学);Huawei Technologies(华为技术有限公司);Tsinghua University(清华大学);Chinese Academy of Sciences(中国科学院)
Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning
Hangzhou Dianzi University(杭州电子科技大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Xi’an Jiaotong University(西安交通大学);Macao Polytechnic University(澳门 polytechnic university)
Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning
School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院);Megvii Research, Megvii Technology Limited(旷视科技有限公司旷视研究院);Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局高性能计算研究所)
Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection
School of Computer Science, China University of Geosciences(中国地质大学(北京)计算机科学学院);State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (CAS)(中国科学院人工智能安全重点实验室);University of China Academy of Sciences(中国科学院大学);Center for Machine Vision and Signal Analysis, University of Oulu(奥卢大学机器视觉与信号分析中心);Microsoft Research Asia(微软亚洲研究院)
DiffusePast: Diffusion-based Generative Replay for Class Incremental Semantic Segmentation
The Hong Kong Polytechnic University(香港理工大学);Center for Artificial Intelligence and Robotics, HKISI, CAS(中国科学院香港创新研究院人工智能与机器人创新中心);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)
Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation
School of Computer Science, University of Nottingham, UK(诺丁汉大学计算机科学学院);School of Artificial Intelligence, Shenzhen University, China(深圳大学人工智能学院);Department of Information Engineering and Computer Science, University of Trento, Italy(特伦托大学信息工程与计算机科学系);School of Computer Science and Information Engineering, Hefei University of Technology, China(合肥工业大学计算机科学与信息工程学院)
Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation
School of Computer Science and Engineering(计算机科学与工程学院);Nanjing University of Science and Technology(南京理工大学);School of Automation Science and Electrical Engineering(自动化科学与电气工程学院);Beihang University(北航);School of Automation and Intelligent Sensing(自动化与智能感知学院);Shanghai Jiao Tong University(上海交通大学)
SAMIC: Segment Anything with In-Context Spatial Prompt Engineering
Department of Computer Science and Engineering(计算机科学与工程系);Schlumberger-Doll Research(斯伦贝谢-多尔研究中心);Department of Civil and Environmental Engineering(土木与环境工程系);The Pennsylvania State University(宾夕法尼亚州立大学)