.png){kind=icon}
返回
Semi-Supervised Domain Generalization with Stochastic StyleMatch
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-023-01821-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Ideally, visual learning algorithms should be generalizable, for dealing with any unseen domain shift when deployed in a new target environment; and data-efficient, for reducing development costs by using as little labels as possible. To this end, we study semi-supervised domain generalization (SSDG), which aims to learn a domain-generalizable model using multi-source, partially-labeled training data. We design two benchmarks that cover state-of-the-art methods developed in two related fields, i.e., domain generalization (DG) and semi-supervised learning (SSL). We find that the DG methods, which by design are unable to handle unlabeled data, perform poorly with limited labels in SSDG; the SSL methods, especially FixMatch, obtain much better results but are still far away from the basic vanilla model trained using full labels. We propose StyleMatch, a simple approach that extends FixMatch with a couple of new ingredients tailored for SSDG: (1) stochastic modeling for reducing overfitting in scarce labels, and (2) multi-view consistency learning for enhancing domain generalization. Despite the concise designs, StyleMatch achieves significant improvements in SSDG. We hope our approach and the comprehensive benchmarks can pave the way for future research on generalizable and data-efficient learning systems. The source code is released at https://github.com/KaiyangZhou/ssdg-benchmark.
Keyword:
Semi-Supervised Domain Generalization
Image recognition
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
A cancer pharmacogenomic screen powering crowd-sourced advancement of drug combination prediction.png)
OAAI
IF0
OAAI分享收藏
查看更多内容