Summary of Cp-prompt: Composition-based Cross-modal Prompting For Domain-incremental Continual Learning, by Yu Feng et al.
CP-Prompt: Composition-Based Cross-modal Prompting for Domain-Incremental Continual Learning
by Yu Feng, Zhen Tian, Yifan Zhu, Zongfu Han, Haoran Luo, Guangwei Zhang, Meina Song
First submitted to arxiv on: 22 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel framework, CP-Prompt, is proposed to tackle the challenge of cross-modal domain-incremental learning (DIL). The method learns from novel data with different feature distributions while avoiding forgetting old ones. It captures intra-domain knowledge by inserting personalized prompts on multi-head self-attention layers and inter-domain common prompting strategy. Experimental results show superiority compared to state-of-the-art baselines across three widely evaluated DIL tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to teach a machine how to learn new things, but it keeps forgetting what it already knows. This is the problem of cross-modal domain-incremental learning (DIL). A team of researchers came up with a clever solution called CP-Prompt. It helps the machine remember old knowledge while learning new things. They tested it on three different tasks and found that it works better than other approaches. |
Keywords
» Artificial intelligence » Prompt » Prompting » Self attention
