Image classification has been widely adopted by current social media applications. Compared with fully supervised classification, semisupervised classification attracts more attention because it is commonly observed that category labels are only available for a small portion of images while most images on social media platforms do not have labels. To this end, we propose a two-stage semisupervised learning framework. In the first stage, we train two Self-supervised Models (SSMs). One model is initialized by predicting the rotation angles of pretransformed training images and then further trained by the labeled images. The other model is initialized by making consistent predictions for the transformed images in color, shape, and quality from the same sample image, and then further trained by the labeled images. In the second stage, we fuse the two SSMs through deep mutual learning, which enhances each of the two SSMs with the complementary information provided by the other such that the correct prediction could be shared. Experimental results on CIFAR and Caltech-256 data sets demonstrate the effect of the proposed framework.

中文翻译：

---

多个自监督模型相互学习的半监督图像分类

图像分类已被当前的社交媒体应用广泛采用。与全监督分类相比，半监督分类更受关注，因为通常观察到类别标签仅适用于一小部分图像，而社交媒体平台上的大多数图像没有标签。为此，我们提出了一个两阶段的半监督学习框架。在第一阶段，我们训练了两个自监督模型（SSM）。一种模型通过预测预变换训练图像的旋转角度来初始化，然后通过标记图像进一步训练。另一个模型通过对来自同一样本图像的变换图像的颜色、形状和质量进行一致的预测来初始化，然后通过标记图像进一步训练。在第二阶段，我们通过深度互学习融合了两个 SSM，这通过另一个 SSM 提供的互补信息来增强两个 SSM 中的每一个，从而可以共享正确的预测。CIFAR 和 Caltech-256 数据集的实验结果证明了所提出框架的效果。