Reasonable classification of aurora is of great significance to the study of the generation mechanism of aurora and the dynamic process of the magnetosphere boundary layer. Previous aurora classification studies, both manual and automatic, rely on experts’ visual inspection and manual labeling of part or all of the data. However, there is currently no consensus on aurora classification schemes. In this paper, an auroral image clustering network (AICNet) is proposed to unsupervised classification of all-sky images for the first time by grouping observations according to their morphological similarities. Auroral features are first extracted by deep convolutional auto-encoder, and the images with similar features are automatically clustered into one group. AICNet is fully automatic and requires no human supervision to tell the classification scheme or manually label samples. In the experiments, 4000 dayside all-sky auroral images captured at the Chinese Yellow River Station during 2003-2008 were considered. The images were clustered into two classes. The occurrence time of auroras illustrates that images in one cluster appear a double-peak occurrence distribution and mostly occur in the afternoon, while images in the other cluster mostly occur before and at noon. Auroral displays in the two clusters exhibit high intra-cluster similarity and low inter-cluster similarity in terms of the overall intensity and morphological structures. Experimental results demonstrate that the proposed method can discover the internal structures of auroras and would enable automatic classification of unprecedented scope without any human supervision.