Summary of Nlprompt: Noise-label Prompt Learning For Vision-language Models, by Bikang Pan et al.
NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
by Bikang Pan, Qun Li, Xiaoying Tang, Wei Huang, Zhen Fang, Feng Liu, Jingya Wang, Jingyi Yu, Ye Shi
First submitted to arxiv on: 2 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: 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 The paper introduces PromptMAE, a new method for prompt learning that uses mean absolute error (MAE) loss to improve robustness against noisy labels while maintaining high accuracy. The authors demonstrate that PromptMAE significantly enhances prompt learning performance in real-world datasets with noisy labels, and show that MAE can suppress the influence of noisy samples, improving the signal-to-noise ratio. The method leverages feature learning theory and is combined with a prompt-based optimal transport data purification method called PromptOT to further enhance robustness. The authors validate their Noise-Label Prompt Learning method, NLPrompt, through extensive experiments across various noise settings, demonstrating significant performance improvements. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses special machines that can understand both pictures and words. These machines are important for many applications like searching for images or understanding what’s in a picture. But sometimes the machines get confused because they have bad information to work with. The new method, called PromptMAE, helps these machines learn better by using a different way of measuring how good their answers are. This makes them less likely to make mistakes when working with bad data. The authors also show how to use another tool called PromptOT to help the machines even more. They tested this new approach and found that it works really well. |
Keywords
» Artificial intelligence » Mae » Prompt
