Learning a Self-Expressive Network for Subspace Clustering

TL;DR

This paper introduces SENet, a neural network-based framework for subspace clustering that generalizes to out-of-sample data and scales well to large datasets, showing competitive results on multiple benchmarks.

Contribution

The paper proposes SENet, a novel neural network model that learns self-expressive representations for subspace clustering, addressing generalization and scalability issues of prior methods.

Findings

SENet effectively handles out-of-sample data.

SENet performs well on large-scale datasets.

Achieves state-of-the-art results on CIFAR-10.

Abstract

State-of-the-art subspace clustering methods are based on self-expressive model, which represents each data point as a linear combination of other data points. However, such methods are designed for a finite sample dataset and lack the ability to generalize to out-of-sample data. Moreover, since the number of self-expressive coefficients grows quadratically with the number of data points, their ability to handle large-scale datasets is often limited. In this paper, we propose a novel framework for subspace clustering, termed Self-Expressive Network (SENet), which employs a properly designed neural network to learn a self-expressive representation of the data. We show that our SENet can not only learn the self-expressive coefficients with desired properties on the training data, but also handle out-of-sample data. Besides, we show that SENet can also be leveraged to perform subspace clustering on large-scale datasets. Extensive experiments conducted on synthetic data and real world benchmark data validate the effectiveness of the proposed method. In particular, SENet yields highly competitive performance on MNIST, Fashion MNIST and Extended MNIST and state-of-the-art performance on CIFAR-10. The code is available at https://github.com/zhangsz1998/Self-Expressive-Network.