DeepVAT: A Self-Supervised Technique for Cluster Assessment in Image Datasets

Alokendu Mazumder, Tirthajit Baruah, Akash Kumar Singh, Krishna Murthy, Vishwajeet Pattanaik, Punit Rathore

Keywords: cluster assessment, VAT, self-supervised learning, dimensionality reduction

Abstract: Estimating the number of clusters and cluster structures in unlabeled, complex, and high-dimensional datasets (like images) is challenging for traditional clustering algorithms. In recent years, a matrix reordering-based algorithm called Visual Assessment of Tendency (VAT), and its variants have attracted many researchers from various domains to estimate the number of clusters and inherent cluster structure present in the data. However, these algorithms face significant challenges when dealing with image data as they fail to effectively capture the crucial features inherent in images. To overcome these limitations, we propose a deep-learning-based framework that enables the assessment of cluster structure in complex image datasets. Our approach utilizes a self-supervised deep neural network to generate representative embeddings for the data. These low-dimensional embeddings are then reduced to 2-dimension using t-distributed Stochastic Neighbour Embedding (t-SNE) and inputted into VAT based algorithms to estimate the underlying cluster structure. Importantly, our framework does not rely on any prior knowledge of the number of clusters. We show that our proposed approach significantly outperforms the state-of-the-art VAT family algorithms and two other deep clustering algorithms on four benchmark datasets including MNIST, FMNIST, CIFAR-10, and INTEL.

Submission Number: 16