Pseudo-supervised Deep Subspace Clustering

by   Juncheng Lv, et al.

Auto-Encoder (AE)-based deep subspace clustering (DSC) methods have achieved impressive performance due to the powerful representation extracted using deep neural networks while prioritizing categorical separability. However, self-reconstruction loss of an AE ignores rich useful relation information and might lead to indiscriminative representation, which inevitably degrades the clustering performance. It is also challenging to learn high-level similarity without feeding semantic labels. Another unsolved problem facing DSC is the huge memory cost due to n× n similarity matrix, which is incurred by the self-expression layer between an encoder and decoder. To tackle these problems, we use pairwise similarity to weigh the reconstruction loss to capture local structure information, while a similarity is learned by the self-expression layer. Pseudo-graphs and pseudo-labels, which allow benefiting from uncertain knowledge acquired during network training, are further employed to supervise similarity learning. Joint learning and iterative training facilitate to obtain an overall optimal solution. Extensive experiments on benchmark datasets demonstrate the superiority of our approach. By combining with the k-nearest neighbors algorithm, we further show that our method can address the large-scale and out-of-sample problems.



There are no comments yet.


page 1

page 6

page 7

page 8

page 9


Overcomplete Deep Subspace Clustering Networks

Deep Subspace Clustering Networks (DSC) provide an efficient solution to...

Maximum Entropy Subspace Clustering Network

Deep subspace clustering network (DSC-Net) and its numerous variants hav...

SPICE: Semantic Pseudo-labeling for Image Clustering

This paper presents SPICE, a Semantic Pseudo-labeling framework for Imag...

Structure Learning with Similarity Preserving

Leveraging on the underlying low-dimensional structure of data, low-rank...

Discrete Optimal Graph Clustering

Graph based clustering is one of the major clustering methods. Most of i...

Multi-Level Representation Learning for Deep Subspace Clustering

This paper proposes a novel deep subspace clustering approach which uses...

Learning Self-Expression Metrics for Scalable and Inductive Subspace Clustering

Subspace clustering has established itself as a state-of-the-art approac...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.