Summary of Generative Dataset Distillation: Balancing Global Structure and Local Details, by Longzhen Li et al.
Generative Dataset Distillation: Balancing Global Structure and Local Details
by Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
First submitted to arxiv on: 26 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- 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 The proposed paper presents a new dataset distillation method that balances global structure and local details when distilling a large dataset into a generative model. The conventional methods face challenges with long redeployment time and poor cross-architecture performance, while previous approaches focused on high-level semantic attributes without considering local features like texture and shape. The authors propose a conditional generative adversarial network-based method that optimizes the generator for more information-dense dataset generation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to make datasets smaller by using a special kind of artificial intelligence called a generative model. Right now, it takes a long time to train these models and they don’t work well across different devices or programs. The authors are trying to solve this problem by creating a method that balances the overall shape of the data with the small details, like texture and shape. They’re using something called a conditional generative adversarial network to make it happen. |
Keywords
» Artificial intelligence » Distillation » Generative adversarial network » Generative model
