Summary of Which Model to Transfer? a Survey on Transferability Estimation, by Yuhe Ding et al.
Which Model to Transfer? A Survey on Transferability Estimation
by Yuhe Ding, Bo Jiang, Aijing Yu, Aihua Zheng, Jian Liang
First submitted to arxiv on: 23 Feb 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 This paper reviews recent advances in estimating the suitability of pre-trained models for specific target tasks without training them individually. The authors categorize existing methods into two realms: source-free model transferability estimation and source-dependent model transferability estimation, providing a comprehensive taxonomy and challenges for future research directions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how to know if a pre-trained model is good for a specific task without having to train it from scratch. It groups different ways of doing this into two types: figuring out if a model works without looking at the source data, and using information from the source data to make an estimate. The authors explain these methods in detail and suggest what needs to be done next. |
Keywords
* Artificial intelligence * Transferability
