Summary of Multi-source Domain Adaptation in the Deep Learning Era: a Systematic Survey, by Sicheng Zhao et al.
Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
by Sicheng Zhao, Bo Li, Colorado Reed, Pengfei Xu, Kurt Keutzer
First submitted to arxiv on: 26 Feb 2020
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
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 In many practical applications, it is often difficult to obtain large-scale labeled data to train deep neural networks. As a result, transferring learned knowledge from a separate source domain to an unlabeled or sparsely labeled target domain becomes appealing. However, direct transfer often results in significant performance decay due to domain shift. Domain adaptation (DA) addresses this problem by minimizing the impact of domain shift between the source and target domains. Multi-source DA is a powerful extension that uses data from multiple sources with different distributions. This paper surveys various MDA strategies, summarizes available datasets for evaluation, compares modern methods like latent space transformation and intermediate domain generation, and discusses future research directions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, researchers are trying to find ways to make computers learn from one kind of data and then apply that learning to another kind of data. This is hard because the two kinds of data might look very different, so it’s like trying to recognize a dog in a picture if you only know what dogs look like from looking at cats. They’re using something called “domain adaptation” to try to make computers better at this. Domain adaptation means taking information learned from one kind of data and using it to help learn from another kind of data. This is important because we often don’t have enough labeled data to train computers, so we need ways to use what we do have. |
Keywords
* Artificial intelligence * Domain adaptation * Latent space
