mlsanityData to 14 Oct 2026

DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype

arXiv 2503.18042 ↗First posted 23 Mar 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Domain-Incremental Learning (DIL) enables vision models to adapt to changing conditions in real-world environments while maintaining the knowledge acquired from previous domains. Given privacy concerns and training time, Rehearsal-Free DIL (RFDIL) is more practical. Inspired by the incremental cognitive process of the human brain, we design Dual-level Concept Prototypes (DualCP) for each class to address the conflict between learning new knowledge and retaining old knowledge in RFDIL. To construct DualCP, we propose a Concept Prototype Generator (CPG) that generates both coarse-grained and fine-grained prototypes for each class. Additionally, we introduce a Coarse-to-Fine calibrator (C2F) to align image features with DualCP. Finally, we propose a Dual Dot-Regression (DDR) loss function to optimize our C2F module. Extensive experiments on the DomainNet, CDDB, and CORe50 datasets demonstrate the effectiveness of our method.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 23 Mar 2025.

Builds on

30 of 50 references.

References · 30

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2016Learning without Forgettingcited by 2,496
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  9. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  10. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  11. 2019Large Scale Incremental Learningcited by 732
  12. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
18 more
  1. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  2. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 289
  3. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  4. 2021Co2L: Contrastive Continual Learningcited by 244
  5. 2018Selective Experience Replay for Lifelong Learningcited by 241
  6. 2020Neural collapse with unconstrained featurescited by 142
  7. 2019Latent Replay for Real-Time Continual Learningcited by 97
  8. 2022On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Featurescited by 97
  9. 2021An Unconstrained Layer-Peeled Perspective on Neural Collapsecited by 87
  10. 2019Incremental learning for the detection and classification of GAN-generated imagescited by 58
  11. 2020Memory Efficient Class-Incremental Learning for Image Classificationcited by 50
  12. 2022A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentialscited by 45
  13. 2021Class-Incremental Learning with Generative Classifierscited by 39
  14. 2023Generalized Neural Collapse for a Large Number of Classescited by 39
  15. 2022CLAD: A realistic Continual Learning benchmark for Autonomous Drivingcited by 36
  16. 2024Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learningcited by 29
  17. 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Modelscited by 14
  18. 2024Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Methodcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Consistent Supervised-Unsupervised Alignment for Generalized Category Discoverycited by 6
  2. 2025Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptationcited by 2
  3. 2025Continual Knowledge Consolidation LORA for Domain Incremental Learningcited by 2
  4. 2026GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discoverycited by 1
  5. 2026We Need a More Robust Classifier: Dual Causal Learning Empowers Domain-Incremental Time Series Classificationcited by 0
  6. 2026StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrievalcited by 0
  7. 2026Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidationcited by 0