Self-Supervised Convolutional Subspace Clustering Network

05/01/2019
by   Junjian Zhang, et al.
0

Subspace clustering methods based on data self-expression have become very popular for learning from data that lie in a union of low-dimensional linear subspaces. However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces. On the other hand, while Convolutional Neural Network (ConvNet) has been demonstrated to be a powerful tool for extracting discriminative features from visual data, training such a ConvNet usually requires a large amount of labeled data, which are unavailable in subspace clustering applications. To achieve simultaneous feature learning and subspace clustering, we propose an end-to-end trainable framework, called Self-Supervised Convolutional Subspace Clustering Network (S^2ConvSCN), that combines a ConvNet module (for feature learning), a self-expression module (for subspace clustering) and a spectral clustering module (for self-supervision) into a joint optimization framework. Particularly, we introduce a dual self-supervision that exploits the output of spectral clustering to supervise the training of the feature learning module (via a classification loss) and the self-expression module (via a spectral clustering loss). Our experiments on four benchmark datasets show the effectiveness of the dual self-supervision and demonstrate superior performance of our proposed approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/10/2022

Self-Supervised Deep Subspace Clustering with Entropy-norm

Auto-Encoder based deep subspace clustering (DSC) is widely used in comp...
research
04/03/2020

Robust Self-Supervised Convolutional Neural Network for Subspace Clustering and Classification

Insufficient capability of existing subspace clustering methods to handl...
research
07/20/2022

Revisiting data augmentation for subspace clustering

Subspace clustering is the classical problem of clustering a collection ...
research
01/19/2020

Multi-Level Representation Learning for Deep Subspace Clustering

This paper proposes a novel deep subspace clustering approach which uses...
research
07/18/2017

Discriminative Transformation Learning for Fuzzy Sparse Subspace Clustering

This paper develops a novel iterative framework for subspace clustering ...
research
05/14/2023

Learning Structure Aware Deep Spectral Embedding

Spectral Embedding (SE) has often been used to map data points from non-...
research
10/06/2021

Exploring the Common Principal Subspace of Deep Features in Neural Networks

We find that different Deep Neural Networks (DNNs) trained with the same...

Please sign up or login with your details

Forgot password? Click here to reset