> For the complete documentation index, see [llms.txt](https://lichangbin.gitbook.io/paper_notes/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lichangbin.gitbook.io/paper_notes/oct/learning-self-train-for-semi-supervised-few-shot-classification.md).

# Learning Self-train for semi-supervised few shot classification

**Motivation**

This paper is not hard to understand, the slide: (<https://drive.google.com/file/d/151ZyvJK77nPJ36LA2gdk3S--8caXS43-/view>) has been very clear.

**Notations**:

* $$\Phi\_{ss}$$ : feature extractor of base learner, one of meta-parameters
* $$\theta$$ : final layer classifier of base learner&#x20;
* $$\theta'$$ : initialization parameters of $$\theta$$ ,  one of meta-parameters
* $$\Phi\_{swn}$$ : weights of soft-weighting network, one of meta-parameters

**Inner loop**:

1. Pseudo-labeling
2. Cherry-picking: (hard selection, soft weighting)
3. Self-training: re-training (S+R), fine-tuning (S)&#x20;

**Outer loop**:

1. update $$\Phi\_{swn}$$ after re-training using the validation loss on query set based on $$\theta\_m$$&#x20;
2. update $$\[\Phi\_{ss}, \theta']$$ after fine-tuning using the validation loss on query set based on $$\theta\_T$$&#x20;

**Reference**

* <https://papers.nips.cc/paper/9216-learning-to-self-train-for-semi-supervised-few-shot-classification.pdf>
* <https://github.com/xinzheli1217/learning-to-self-train>
* <https://drive.google.com/file/d/151ZyvJK77nPJ36LA2gdk3S--8caXS43-/view>
* <https://qianrusun.com/>