Research map / Vision-language and multimodal / Cross-modal learning
Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning
Jiong Yin, Liang Li, Jiehua Zhang, Yuhan Gao, Chenggang Yan, Xichun Sheng
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 three-stage progressive prompts (TMA, TMDG, TMI) to the prompt-based incremental learner | PHP · AVE/AVVP/AVQA incremental | mean forgetting (F_mean avg): 4.59 -> 3.32 | Improved |
| use PHP instead of best baseline PC for transfer | PHP · AVE/AVVP/AVQA multi-task transfer | normalized transfer (Diff): -3.94% -> +7.79% | Improved |
| add TMA adapter alone to baseline (ablation) | PHP · AVE/AVVP/AVQA multi-task transfer | normalized transfer (Diff): -6.10% -> +8.05% | Improved |
| add TMDG and TMI without the TMA adapter (ablation) | PHP · AVE/AVVP/AVQA multi-task transfer | normalized transfer (Diff): +7.77% -> -0.71% | Hurt |
| add TMA and TMDG together (no TMI) (ablation) | PHP · AVE/AVVP/AVQA incremental (anti-forgetting) | mean forgetting (F_mean avg): 4.20 -> 3.21 | Improved |
| add all three components versus baseline on mean accuracy (ablation) | PHP · AVE/AVVP/AVQA incremental (anti-forgetting) | mean accuracy (A_mean avg): 58.20 -> 58.85 | No clear effect |
| place components in shallow-middle-deep order (S-M-D) instead of other orderings (ablation) | PHP · AVE/AVVP/AVQA incremental (component order) | mean accuracy (A_mean): 49.12 -> 58.85 | Improved |
| increase deep prompt length (ablation) | PHP · AVE->AVQA->AVVP sequence | forgetting vs transfer | Mixed |
| increase number of task-specific layers (ablation) | PHP · AVE->AVQA->AVVP sequence | AVE and AVVP performance | Hurt |
| train tasks incrementally (LLP->AVE) instead of single-task AVE (ablation) | PHP · AVE | accuracy: 70.03% -> 73.23% | Improved |
| PHP versus Dualprompt on AVE final accuracy | PHP · AVE (incremental) | final accuracy: 58.10 -> 55.00 | Hurt |
Closest papers by meaning
- Few-Shot Audio-Visual Class-Incremental Learning with Temporal Prompting and Regularization (AAAI 2025 · similarity 0.89)
- Continual Audio-Visual Sound Separation (NeurIPS 2024 · similarity 0.88)
- Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning (NeurIPS 2026 · similarity 0.88)
- MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning (AAAI 2024 · similarity 0.86)
- Exploring the Transferability of Visual Prompting for Multimodal Large Language Models (CVPR 2024 · similarity 0.86)
- Mixtures of Experts for Audio-Visual Learning (NeurIPS 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.
