Summary of Source-free Domain Adaptation Guided by Vision and Vision-language Pre-training, By Wenyu Zhang and Li Shen and Chuan-sheng Foo
Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training
by Wenyu Zhang, Li Shen, Chuan-Sheng Foo
First submitted to arxiv on: 5 May 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 proposed framework integrates pre-trained networks into the source-free domain adaptation (SFDA) process to leverage their representation learning capabilities. The Co-learn algorithm improves target pseudolabel quality collaboratively through the source model and a pre-trained feature extractor. This is extended with CLIP’s zero-shot classification decisions in Co-learn++. The method is evaluated on 4 benchmark datasets, including open-set, partial-set, and open-partial SFDA scenarios. Results show improved adaptation performance and integration with existing methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new way to adapt a model trained on one set of data to work well on another similar but different set of data. It uses pre-trained models that were trained on many images or texts to help the adapted model learn better. The method is tested on several datasets and shows that it can improve the results. This means that the adapted model will be more accurate when working with new, unseen data. |
Keywords
» Artificial intelligence » Classification » Domain adaptation » Representation learning » Zero shot
