Improving Deep Image Clustering With Spatial Transformer Layers

Deep image clustering is a recent research area, but with exciting published works [15]. The approaches use the most diverse architectures varying the structure of the deep networks, theclustering algorithms and the combination of both parts. Approachessuch as the Deep Clustering Network (DCN) [9] use a pretrained autoencoder combined with the k-means algorithm. Methods such as Joint Unsupervised Learning (JULE) [10] combines deep convolutional networks with hierarchical clustering. Deep Embbed Cluster (DEC) [11], also uses a pretrained autoencoder, then removes the decoder part and uses the encoder as a feature extractor to feed the clustering method. After that, the network is fine-tuned using the cluster assignment hardening loss. Meanwhile, the clusters are iteratively tuned by minimizing the KL-divergence between the distribution of soft labels and the auxiliary target distribution.