In an effort to further advance semi-supervised generative and classification tasks, we propose a simple yet effective training strategy called dual pseudo training (DPT), built upon strong semi-supervised learners and diffusion models. DPT operates in three stages: training a classifier on partially labeled data to predict pseudo-labels; training a conditional generative model using these pseudo-labels to generate pseudo images; and retraining the classifier with a mix of real and pseudo images. Empirically, DPT consistently achieves SOTA performance of semi-supervised generation and classification across various settings. In particular, with one or two labels per class, DPT achieves a Fr\'echet Inception Distance (FID) score of 3.08 or 2.52 on ImageNet 256x256. Besides, DPT outperforms competitive semi-supervised baselines substantially on ImageNet classification tasks, achieving top-1 accuracies of 59.0 (+2.8), 69.5 (+3.0), and 74.4 (+2.0) with one, two, or five labels per class, respectively. Notably, our results demonstrate that diffusion can generate realistic images with only a few labels (e.g., <0.1%) and generative augmentation remains viable for semi-supervised classification. Our code is available at https://github.com/ML-GSAI/DPT.

翻译：为推进半监督生成与分类任务，我们提出一种简单而有效的训练策略——双重伪训练（DPT），该策略基于强半监督学习器与扩散模型构建。DPT包含三个阶段：利用部分标签数据训练分类器以预测伪标签；使用这些伪标签训练条件生成模型生成伪图像；最后用真实图像与伪图像的混合数据重新训练分类器。实验表明，DPT在不同设置下均实现了半监督生成与分类的最新性能（SOTA）。特别地，在每类仅含一个或两个标签时，DPT在ImageNet 256×256数据集上的弗雷歇初始距离（FID）评分分别达到3.08和2.52。此外，在ImageNet分类任务中，DPT显著超越竞争性半监督基线：每类含一、二或五个标签时，Top-1准确率分别达59.0%（+2.8）、69.5%（+3.0）和74.4%（+2.0）。值得注意的是，我们的结果表明，扩散模型能在极少量标签（如<0.1%）下生成逼真图像，且生成增强对半监督分类依然可行。代码已开源：https://github.com/ML-GSAI/DPT。