Unsupervised Deep Clustering of MNIST with Triplet-Enhanced Convolutional Autoencoders

TL;DR

This paper presents a novel unsupervised deep clustering method for MNIST that combines autoencoders with a joint clustering loss, achieving high-quality, interpretable digit clusters with scalable implementation.

Contribution

It introduces a two-phase deep autoencoder architecture with a combined reconstruction and clustering loss, enhancing unsupervised image clustering performance.

Findings

Achieved superior clustering metrics on MNIST

Generated clear, distinct digit clusters in embeddings

Demonstrated scalable and stable training process

Abstract

This research implements an advanced unsupervised clustering system for MNIST handwritten digits through two-phase deep autoencoder architecture. A deep neural autoencoder requires a training process during phase one to develop minimal yet interpretive representations of images by minimizing reconstruction errors. During the second phase we unify the reconstruction error with a KMeans clustering loss for learned latent embeddings through a joint distance-based objective. Our model contains three elements which include batch normalization combined with dropout and weight decay for achieving generalized and stable results. The framework achieves superior clustering performance during extensive tests which used intrinsic measurements including Silhouette Score and Davies-Bouldin Index coupled with extrinsic metrics NMI and ARI when processing image features. The research uses t-SNE visualization to present learned embeddings that show distinct clusters for digits. Our approach reaches an optimal combination between data reconstruction accuracy and cluster separation purity when adding the benefit of understandable results and scalable implementations. The approach creates a dependable base that helps deploy unsupervised representation learning in different large-scale image clustering applications.