DeepVAT: A Self-Supervised Technique for Cluster Assessment in Image Datasets
This work addresses the problem of cluster assessment in complex image data for researchers and practitioners in machine learning and data analysis, representing an incremental improvement over existing VAT-based methods.
The paper tackles the challenge of estimating cluster structures in unlabeled image datasets by proposing DeepVAT, a self-supervised deep learning framework that generates embeddings for input into VAT-based algorithms, achieving superior performance over state-of-the-art methods on benchmark datasets like MNIST, FMNIST, CIFAR-10, and INTEL.
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 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. Our proposed approach demonstrates superior performance compared to state-of-the-art VAT family algorithms and two other deep clustering algorithms on four benchmark image datasets, namely MNIST, FMNIST, CIFAR-10, and INTEL.