> For the complete documentation index, see [llms.txt](https://blog.tsingjyujing.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://blog.tsingjyujing.com/ml/common/semi-supervised-learning.md).

# 半监督/无监督学习

## 无监督

* [Unsupervised Moving Object Detection](https://arxiv.org/pdf/1901.03360.pdf)
  * [antonilo/unsupervised\_detection](https://github.com/antonilo/unsupervised_detection)
* [Self-training with Noisy Student improves ImageNet classification](https://arxiv.org/abs/1911.04252)
  * [Self-training with Noisy Student](https://zhuanlan.zhihu.com/p/164597142)
  * [Self-training在目标检测任务上的实践](https://www.jiqizhixin.com/articles/2020-08-03-6)
* [Unsupervised learning of foreground object detection](https://arxiv.org/pdf/1808.04593.pdf)
* [何恺明一作，刷新7项检测分割任务，无监督预训练完胜有监督](https://www.jiqizhixin.com/articles/2019-11-15-6)
* [2020年国内最新最优目标检测（完结篇）](https://cloud.tencent.com/developer/article/1613547)
* [目标检测算法进展大盘点](https://zhuanlan.zhihu.com/p/112942266)
* [AAAI 2020 论文解读：商汤科技提出新弱监督目标检测框架](https://www.infoq.cn/article/yzldalqwipqbijo5xlah)

## 半监督/弱监督

* [ICLR2021 Oral ｜利用一个样本估计类别数据分布 9行代码提高少样本学习泛化能力](https://zhuanlan.zhihu.com/p/344531704)
  * 只适合分类问题


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://blog.tsingjyujing.com/ml/common/semi-supervised-learning.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.