mlsanityData to 7 Oct 2026

CP-Prompt: Composition-Based Cross-modal Prompting for Domain-Incremental Continual Learning

arXiv 2407.21043 ↗First posted 22 Jul 2024cs.CL cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

The key challenge of cross-modal domain-incremental learning (DIL) is to enable the learning model to continuously learn from novel data with different feature distributions under the same task without forgetting old ones. However, existing top-performing methods still cause high forgetting rates, by lacking intra-domain knowledge extraction and inter-domain common prompting strategy. In this paper, we propose a simple yet effective framework, CP-Prompt, by training limited parameters to instruct a pre-trained model to learn new domains and avoid forgetting existing feature distributions. CP-Prompt captures intra-domain knowledge by compositionally inserting personalized prompts on multi-head self-attention layers and then learns the inter-domain knowledge with a common prompting strategy. CP-Prompt shows superiority compared with state-of-the-art baselines among three widely evaluated DIL tasks. The source code is available at https://github.com/dannis97500/CP_Prompt.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 22 Jul 2024.

Builds on

35 of 54 references.

References · 35

  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  8. 2016Learning without Forgettingcited by 2,465
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  10. 2016Concrete Problems in AI Safetycited by 1,582
  11. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  12. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
23 more
  1. 2018Experience Replay for Continual Learningcited by 1,074
  2. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  3. 2021Learning to Prompt for Continual Learningcited by 938
  4. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  5. 2019Large Scale Incremental Learningcited by 727
  6. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  7. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  8. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  9. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  10. 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 246
  11. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  12. 2021Co2L: Contrastive Continual Learningcited by 243
  13. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  14. 2021Self-Supervised Models are Continual Learnerscited by 149
  15. 2022PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Modelcited by 133
  16. 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimalitycited by 121
  17. 2020A Comprehensive Study of Class Incremental Learning Algorithms for Visual Taskscited by 107
  18. 2018Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilizationcited by 104
  19. 2020Continual Deep Learning by Functional Regularisation of Memorable Pastcited by 104
  20. 2019Latent Replay for Real-Time Continual Learningcited by 97
  21. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  22. 2022A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentialscited by 45
  23. 2021CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Taskscited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025Componential Prompt-Knowledge Alignment for Domain Incremental Learningcited by 13
  2. 2025Multiple Queries with Multiple Keys: A Precise Prompt Matching Paradigm for Prompt-based Continual Learningcited by 1
  3. 2025Resilient Multimodal Industrial Surface Defect Detection with Uncertain Sensors Availabilitycited by 1
  4. 2026Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuningcited by 1
  5. 2026Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learningcited by 1
  6. 20265% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuningcited by 1
  7. 2025Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptationcited by 0
  8. 2025Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detectioncited by 0
  9. 2026When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learningcited by 0
  10. 2026HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learningcited by 0
  11. 2026Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidationcited by 0