Research map / Continual learning / Domain and prompt-based
Lifelong Domain Adaptation via Consolidated Internal Distribution
Mohammad Rostami
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 |
|---|---|---|---|
| use LDAuCID adaptation instead of no adaptation (source only) (ablation) | VGG16 / ResNet-50 models · SVHN->MNIST | accuracy: 67.3±2.6 -> 91.4 ± 2.2 | Improved |
| use LDAuCID adaptation instead of no adaptation (source only) (ablation) | ResNet-50 · Office-Home average | accuracy: 46.1 -> 59.4 | Improved |
| use LDAuCID without source data instead of joint-training UDA methods (CDAN) | LDAuCID · Office-Home average | accuracy: 63.9 -> 59.4 | Hurt |
| use LDAuCID instead of ETD | LDAuCID · SVHN->MNIST | accuracy: 97.9± 0.4 -> 91.4 ± 2.2 | Hurt |
| use LDAuCID instead of ETD | LDAuCID · ImageCLEF-DA average | accuracy: 89.7 -> 95.8 | Improved |
| increase memory buffer size from 50 to 100 samples (ablation) | LDAuCID · S->M->U, USPS | accuracy: 91.9 -> 94.6 | Improved |
| make training data imbalanced across digit classes (ablation) | LDAuCID · S->M->U, USPS | accuracy: 93.1 on imbalanced data (balanced value not tabulated) | Hurt |
| vary trade-off parameter lambda (ablation) | LDAuCID · SVHN->MNIST | accuracy | No clear effect |
| raise pseudo-sample confidence threshold tau toward 1 (ablation) | LDAuCID · SVHN->MNIST | accuracy | Improved |
Closest papers by meaning
- On Generalizing Beyond Domains in Cross-Domain Continual Learning (CVPR 2022 · similarity 0.92)
- Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning (ICCV 2023 · similarity 0.92)
- A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability (CVPR 2024 · similarity 0.86)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.86)
- Model Sensitivity Aware Continual Learning (NeurIPS 2024 · similarity 0.86)
- ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation (ICLR 2024 · similarity 0.86)
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.
