Research map / Continual learning / Domain and prompt-based
Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation
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 |
|---|---|---|---|
| Adapt inputs with domain-specific and domain-agnostic visual prompts while freezing the source model | CTAP · CIFAR100-to-CIFAR100C, severity 5 | error rate (%): 32.5 -> 16.8 | Helped |
| Adapt inputs with domain-specific and domain-agnostic visual prompts while freezing the source model | CTAP · CIFAR10-to-CIFAR10C, severity 5 | error rate (%): 16.2 -> 13.9 | Helped |
| Adapt inputs with domain-specific and domain-agnostic visual prompts while freezing the source model | CTAP · CIFAR10-to-CIFAR10C gradual | error rate (%): 10.4 -> 6.1 | Helped |
| Adapt inputs with domain-specific and domain-agnostic visual prompts while freezing the source model | CTAP · ImageNet-to-ImageNet-C, severity 5 | error rate (%): 63.0 -> 51.5 | Helped |
| Adapt inputs with visual prompts instead of relying on model updates | CTAP · VLCS, source VOC2007, rounds 1–3 | mean error rate (%): 57.5 -> 41.6 | Helped |
| Add DSP and DAP rather than using no prompts (ablation) | CTAP · CIFAR10C | error rate (%): 16.2 -> 13.9 | Helped |
| Add DSP and DAP rather than using no prompts (ablation) | CTAP · CIFAR100C | error rate (%): 32.5 -> 16.3 | Helped |
| Add DSP and DAP rather than using no prompts (ablation) | CTAP · ImageNet-C | error rate (%): 63.0 -> 51.5 | Helped |
| Add DAP to DSP (ablation) | CTAP · CIFAR10C | error rate (%): 14.9 -> 13.9 | Helped |
| Add DAP to DSP (ablation) | CTAP · CIFAR100C | error rate (%): 17.8 -> 16.3 | Helped |
| Add DAP to DSP (ablation) | CTAP · ImageNet-C | error rate (%): 52.4 -> 51.5 | Helped |
| Add DSP to DAP (ablation) | CTAP · CIFAR10C | error rate (%): 15.2 -> 13.9 | Helped |
Closest papers by meaning
- DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation (ICML 2025 · similarity 0.93)
- A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability (CVPR 2024 · similarity 0.92)
- ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation (ICLR 2024 · similarity 0.91)
- Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation (CVPR 2024 · similarity 0.90)
- PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation (AAAI 2025 · similarity 0.90)
- ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains (NeurIPS 2025 · similarity 0.90)
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.