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.

Overview

Publication

Seon-Ho Lee and Chang-Su Kim, "Deep Repulsive Clustering of Ordered Data Based on Order-Identity Decomposition," accepted to International Conference on Learning Representations (ICLR), 2021.
[paper] [code]