Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use LDDG instead of the strongest reported baseline | ResNet18 skin lesion classifier · Skin lesion classification (six target datasets), Avg | accuracy: 0.6460 -> 0.6697 | Helped |
| Use LDDG instead of CCSA | ResNet18 skin lesion classifier · Skin lesion classification (HAM10000 source), Avg | accuracy: 0.4582 -> 0.5231 | Helped |
| Use LDDG instead of MASF | 2D-UNet spinal cord segmentation · Spinal cord gray matter segmentation, Avg | DSC: 0.7710 -> 0.7881 | Helped |
| Add the proposed rank regularization (ablation) | LDDG · Skin lesion classification, UDA target | accuracy | Helped |
| Add KL distribution alignment (ablation) | LDDG · Skin lesion classification, UDA target | accuracy | Helped |
| Use category-targeted rank regularization instead of nuclear-norm low-rank regularization (ablation) | LDDG · Skin lesion classification, UDA target | accuracy | Helped |
| Set latent feature rank to the number of task categories (ablation) | LDDG · Skin lesion classification, UDA target | accuracy | Mixed |
| Apply BigAug with default parameters | 2D-UNet spinal cord segmentation · Spinal cord gray matter segmentation, Avg | DSC: 0.7425 -> 0.7348 | Hurt |
| Tune BigAug parameters | 2D-UNet spinal cord segmentation · Spinal cord gray matter segmentation, Avg | DSC: 0.7425 -> 0.7647 | Helped |
| Vary latent feature rank above the peak value (ablation) | LDDG · Skin lesion classification, UDA target | accuracy | Hurt |
Closest papers by meaning
- The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images (ICLR 2024 · similarity 0.87)
- TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging (ICML 2025 · similarity 0.86)
- Learning Generalized Medical Image Segmentation from Decoupled Feature Queries (AAAI 2024 · similarity 0.86)
- Perturbating, Tuning, and Collaborating: Harnessing Vision Foundation Models for Single Domain Generalization on Medical Imaging (AAAI 2025 · similarity 0.86)
- Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention (CVPR 2024 · similarity 0.84)
- A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis (NeurIPS 2024 · similarity 0.84)
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.