Summary of Pearl: Input-agnostic Prompt Enhancement with Negative Feedback Regulation For Class-incremental Learning, by Yongchun Qin et al.
PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning
by Yongchun Qin, Pengfei Fang, Hui Xue
First submitted to arxiv on: 14 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 In this paper, researchers propose a novel approach to class-incremental learning (CIL), called PEARL, which leverages pre-trained models (PTMs) to continuously introduce new categories into a classification system without forgetting previously learned ones. The authors critically examine the limitations of existing methods and implement an input-agnostic global prompt with an adaptive momentum update strategy to reduce the model’s dependency on data distribution. This approach mitigates catastrophic forgetting and fosters continuous enhancement of the prompt for new tasks by harnessing correlations between different tasks in CIL. The proposed method achieves state-of-the-art performance on six benchmarks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Class-incremental learning is a way to teach machines to learn from new categories without forgetting old ones. Researchers are trying to use pre-trained models to make this process better. They’re proposing a new approach called PEARL that uses a special kind of prompt to help the model learn from new data. This approach helps the model remember what it learned before and adapt to new information. The authors tested their method on several datasets and found that it performed very well. |
Keywords
» Artificial intelligence » Classification » Prompt
