Research map / Continual learning / Domain and prompt-based
DK-DDIL: Adaptive Knowledge Retention for Dynamic Domain-Incremental Learning in Medical Imaging
Yuxi Ma, Sujie Liu, Jing Yang, Jiacheng Wang, Yiping Chen, Baptiste Magnier, Liansheng Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add DAM (dynamic rank LoRA) to classifier-only fine-tuning (ablation) | FT · Skin Pathology Diagnosis | average accuracy A: 52.96 -> 75.56 | Improved |
| add DCL to classifier-only fine-tuning (ablation) | FT · Skin Pathology Diagnosis | average accuracy A: 52.96 -> 52.98 | No clear effect |
| add DCL on top of DAM (ablation) | FT+DAM · Skin Pathology Diagnosis | final accuracy AT: 68.68 -> 70.88 | Improved |
| add MKI on top of DAM (ablation) | FT+DAM · Skin Pathology Diagnosis | average accuracy A: 75.56 -> 75.57 | No clear effect |
| add MKI and DCL together on top of DAM (ablation) | FT+DAM · Skin Pathology Diagnosis | final accuracy AT: 68.68 -> 71.52 | Improved |
| insert DAM into all layers instead of even layers only (ablation) | DK-DDIL · Skin Pathology Diagnosis | average accuracy A: 73.02 -> 77.03 | Improved |
| insert DAM into odd layers only instead of all layers (ablation) | DK-DDIL · Skin Pathology Diagnosis | average accuracy A: 77.03 -> 76.97 | No clear effect |
| apply DAM to all projections instead of Q only (ablation) | DK-DDIL · Skin Pathology Diagnosis | average accuracy A: 72.23 -> 77.03 | Improved |
| raise alpha_init from 0.1 to 0.3 (ablation) | DK-DDIL · Skin Pathology Diagnosis | average accuracy A: 77.03 -> 77.71 | Mixed |
| DK-DDIL vs best baseline on OfficeHome | Domain-incremental learning · OfficeHome | average accuracy A: 82.22 -> 84.35 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- RanPAC — RanPAC: Random Projections and Pre-trained Models for Continual Learning (NeurIPS 2023) · better on 6 of 6 shared results
- CL-LoRA — CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning (CVPR 2025) · better on 2 of 2 shared results
- DualPrompt — DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning (ECCV 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · similarity 0.89)
- Perturbating, Tuning, and Collaborating: Harnessing Vision Foundation Models for Single Domain Generalization on Medical Imaging (AAAI 2025 · similarity 0.88)
- A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis (NeurIPS 2024 · similarity 0.87)
- Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback (NeurIPS 2025 · similarity 0.86)
- AIF-SFDA: Autonomous Information Filter Driven Source-Free Domain Adaptation for Medical Image Segmentation (AAAI 2025 · similarity 0.85)
- Autoregressive Sequence Modeling for 3D Medical Image Representation (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
