Deep Discriminative Clustering Analysis
This addresses clustering inefficiencies in deep learning for domains like image, text, and audio, though it appears incremental as it builds on existing deep clustering approaches.
The paper tackles the problem of traditional clustering methods using low-level representations by developing Deep Discriminative Clustering (DDC), which models clustering with deep neural networks to learn high-level discriminative representations and relationships between patterns, resulting in outperforming current methods on eight diverse datasets.
Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning. To handle this problem, we develop Deep Discriminative Clustering (DDC) that models the clustering task by investigating relationships between patterns with a deep neural network. Technically, a global constraint is introduced to adaptively estimate the relationships, and a local constraint is developed to endow the network with the capability of learning high-level discriminative representations. By iteratively training the network and estimating the relationships in a mini-batch manner, DDC theoretically converges and the trained network enables to generate a group of discriminative representations that can be treated as clustering centers for straightway clustering. Extensive experiments strongly demonstrate that DDC outperforms current methods on eight image, text and audio datasets concurrently.