Research map / Continual learning / Class-incremental
Semantic-Guided Global-Local Collaborative Prompt Learning for Few-Shot Class Incremental Learning
Yongxin Yan, Weisen Chen, Xingye Chen, Yuanjie Shao, Zhengrong Zuo, Wenming Tan, Wenqi Ren, Changxin Gao, Nong Sang
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 Global-Level prompt learning to the CLIP baseline (ablation) | SGLC · CUB200 (FSCIL) | Aavg: 58.09 -> 78.04 | Improved |
| add Local-Level prompt learning (optimal transport) on top of global (ablation) | SGLC · CUB200 (FSCIL) | Aavg: 78.04 -> 79.08 | Improved |
| add Semantic-Guided LLM description distillation (ablation) | SGLC · CUB200 (FSCIL) | Aavg: 79.08 -> 80.18 | Improved |
| add learnable deep-layer prompts to CoOp (ablation) | CoOp · CUB200 (FSCIL) | Aavg: 69.47 -> 71.22 | Improved |
| add adapter-based visual feature correction to CoOp (ablation) | CoOp · CUB200 (FSCIL) | Aavg: 69.47 -> 70.72 | Improved |
| combine deep-layer prompts and visual feature correction (ablation) | CoOp · CUB200 (FSCIL) | Aavg: 69.47 -> 72.53 | Improved |
| use more LLM-selected attributes (add pattern) (ablation) | SGLC local prompts · CUB200 (FSCIL) | Aavg: 80.18 -> 79.63 | Hurt |
| use four attributes (add pattern and size) (ablation) | SGLC local prompts · CUB200 (FSCIL) | Aavg: 80.18 -> 79.01 | Hurt |
| replace one-to-one cosine alignment with optimal transport in local alignment (ablation) | SGLC · CUB200 (FSCIL) | accuracy per session | Improved |
| use category-specific prompts with frozen old-class prompts instead of category-agnostic prompts (ablation) | SGLC global prompts · CUB200 (FSCIL) | base-class accuracy across sessions | Improved |
| train only 0.71M parameters via prompts and adapter instead of full fine-tuning | SGLC · CUB200 (FSCIL) | trainable parameters: 86.68M -> 0.71M | Improved |
Closest papers by meaning
- Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners (CVPR 2024 · similarity 0.90)
- SEC-Prompt:SEmantic Complementary Prompting for Few-Shot Class-Incremental Learning (CVPR 2025 · similarity 0.90)
- VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning (NeurIPS 2025 · similarity 0.88)
- Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning (CVPR 2025 · similarity 0.87)
- CoPL: Contextual Prompt Learning for Vision-Language Understanding (AAAI 2024 · similarity 0.87)
- Making Large Vision Language Models to Be Good Few-Shot Learners (AAAI 2025 · similarity 0.87)
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.
