Research map / Continual learning / Domain and prompt-based
Introducing Language Guidance in Prompt-based Continual Learning
Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal
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 language guidance (LGCL) to DualPrompt | DualPrompt · Split ImageNet-R | average accuracy (%): 68.13 -> 69.46 | Improved |
| add language guidance (LGCL) to DualPrompt | DualPrompt · Split CIFAR-100 | average accuracy (%): 86.51 -> 87.23 | Improved |
| add language guidance (LGCL) to L2P | L2P · Split CIFAR-100 | forgetting (%): 7.35 -> 5.83 | Improved |
| add language guidance (LGCL) to L2P | L2P · Split ImageNet-R | average accuracy (%): 61.57 -> 62.51 | Improved |
| add task-level language loss only (ablation) | DualPrompt · Split ImageNet-R | average accuracy (%): 68.13 -> 69.43 | Improved |
| add class-level language loss only (ablation) | L2P · Split ImageNet-R | average accuracy (%): 61.57 -> 62.36 | Improved |
| add both task-level and class-level losses (ablation) | DualPrompt · Split ImageNet-R | average accuracy (%): 68.13 -> 69.46 | Improved |
| use CLIP text encoder instead of BERT or RoBERTa (ablation) | DualPrompt + LGCL · Split CIFAR-100 | average accuracy (%): 87.04 (RoBERTa), 87.11 (BERT) -> 87.23 | Improved |
| use learnable keys instead of frozen CLIP text keys (ablation) | DualPrompt + LGCL · Split CIFAR-100 | average accuracy (%): 86.15 -> 87.23 | Improved |
| use frozen CLIP keys instead of learnable keys (ablation) | DualPrompt + LGCL · Split CIFAR-100 | forgetting (%): 5.10 -> 3.93 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DualPrompt — DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning (ECCV 2022) · better on 4 of 4 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
- Convolutional Prompting meets Language Models for Continual Learning (CVPR 2024 · similarity 0.92)
- Learning To Prompt for Continual Learning (CVPR 2022 · similarity 0.92)
- Advancing Prompt-Based Methods for Replay-Independent General Continual Learning (ICLR 2025 · similarity 0.91)
- Mixture of Experts Meets Prompt-Based Continual Learning (NeurIPS 2024 · similarity 0.90)
- Enhancing Visual Continual Learning with Language-Guided Supervision (CVPR 2024 · similarity 0.90)
- REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning (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.
