Summary of Mitigating Label Noise Using Prompt-based Hyperbolic Meta-learning in Open-set Domain Generalization, by Kunyu Peng et al.
Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
by Kunyu Peng, Di Wen, Sarfraz M. Saquib, Yufan Chen, Junwei Zheng, David Schneider, Kailun Yang, Jiamin Wu, Alina Roitberg, Rainer Stiefelhagen
First submitted to arxiv on: 24 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Image and Video Processing (eess.IV)
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 proposed Open-Set Domain Generalization (OSDG) framework, HyProMeta, tackles the challenging task of accurately predicting familiar categories while minimizing confidence for unknown categories in unseen domains. The framework integrates hyperbolic category prototypes for label noise-aware meta-learning and a learnable new-category agnostic prompt to enhance generalization to unseen classes. This approach is evaluated on dedicated benchmarks derived from widely used OSDG datasets, including PACS and DigitsDG, outperforming state-of-the-art methods. The study highlights the limitations of existing strategies in handling label noise effectively and proposes a novel framework that addresses this challenge. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary HyProMeta is a new way to help computers learn about things they haven’t seen before. It’s called Open-Set Domain Generalization, or OSDG for short. The goal is to teach machines to recognize familiar things, like dogs or cars, while also saying “I don’t know” when they see something new, like a weird animal. This task is tricky because sometimes the information we give computers is wrong, and that can make it harder for them to learn. In this study, researchers created special tests to see how well different approaches work in these noisy conditions. They found that their new approach, HyProMeta, does better than others at recognizing things it hasn’t seen before. |
Keywords
» Artificial intelligence » Domain generalization » Generalization » Meta learning » Prompt
