Deep Repulsive Clustering of Ordered Data Based on Order-Identity Decomposition

Seon-Ho Lee, Chang-Su Kim

Keywords: Clustering, order learning, age estimation, aesthetic assessment, historical color image classification

Abstract: We propose the deep repulsive clustering (DRC) algorithm of ordered data for effective order learning. First, we develop the order-identity decomposition (ORID) network to divide the information of an object instance into an order-related feature and an identity feature. Then, we group object instances into clusters according to their identity features using a repulsive term. Moreover, we estimate the rank of a test instance, by comparing it with references within the same cluster. Experimental results on facial age estimation, aesthetic score regression, and historical color image classification show that the proposed algorithm can cluster ordered data effectively and also yield excellent rank estimation performance.

One-sentence Summary: A deep clustering algorithm for ordered data is proposed based on the order-identity decomposition.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Data: [MORPH](https://paperswithcode.com/dataset/morph)