SA-Net: A deep spectral analysis network for image clustering
- URL: http://arxiv.org/abs/2009.07026v1
- Date: Fri, 11 Sep 2020 05:27:23 GMT
- Title: SA-Net: A deep spectral analysis network for image clustering
- Authors: Jinghua Wang and Jianmin Jiang
- Abstract summary: We propose a deep spectral analysis network for unsupervised representation learning and image clustering.
The SA-Net has the capability to learn deep representations and reveal deep correlations among data samples.
Our proposed SA-Net outperforms 11 benchmarks across a number of image clustering applications.
- Score: 31.334196673143257
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Although supervised deep representation learning has attracted enormous
attentions across areas of pattern recognition and computer vision, little
progress has been made towards unsupervised deep representation learning for
image clustering. In this paper, we propose a deep spectral analysis network
for unsupervised representation learning and image clustering. While spectral
analysis is established with solid theoretical foundations and has been widely
applied to unsupervised data mining, its essential weakness lies in the fact
that it is difficult to construct a proper affinity matrix and determine the
involving Laplacian matrix for a given dataset. In this paper, we propose a
SA-Net to overcome these weaknesses and achieve improved image clustering by
extending the spectral analysis procedure into a deep learning framework with
multiple layers. The SA-Net has the capability to learn deep representations
and reveal deep correlations among data samples. Compared with the existing
spectral analysis, the SA-Net achieves two advantages: (i) Given the fact that
one spectral analysis procedure can only deal with one subset of the given
dataset, our proposed SA-Net elegantly integrates multiple parallel and
consecutive spectral analysis procedures together to enable interactive
learning across different units towards a coordinated clustering model; (ii)
Our SA-Net can identify the local similarities among different images at patch
level and hence achieves a higher level of robustness against occlusions.
Extensive experiments on a number of popular datasets support that our proposed
SA-Net outperforms 11 benchmarks across a number of image clustering
applications.
Related papers
- Spectral Graph Reasoning Network for Hyperspectral Image Classification [0.43512163406551996]
Convolutional neural networks (CNNs) have achieved remarkable performance in hyperspectral image (HSI) classification.
We propose a spectral graph reasoning network (SGR) learning framework comprising two crucial modules.
Experiments on two HSI datasets demonstrate that the proposed architecture can significantly improve the classification accuracy.
arXiv Detail & Related papers (2024-07-02T20:29:23Z) - DiffSpectralNet : Unveiling the Potential of Diffusion Models for
Hyperspectral Image Classification [6.521187080027966]
We propose a new network called DiffSpectralNet, which combines diffusion and transformer techniques.
First, we use an unsupervised learning framework based on the diffusion model to extract both high-level and low-level spectral-spatial features.
The diffusion method is capable of extracting diverse and meaningful spectral-spatial features, leading to improvement in HSI classification.
arXiv Detail & Related papers (2023-10-29T15:26:37Z) - ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and
Multispectral Data Fusion [54.668445421149364]
Deep learning-based hyperspectral image (HSI) super-resolution aims to generate high spatial resolution HSI (HR-HSI) by fusing hyperspectral image (HSI) and multispectral image (MSI) with deep neural networks (DNNs)
In this letter, we propose a novel adversarial automatic data augmentation framework ADASR that automatically optimize and augments HSI-MSI sample pairs to enrich data diversity for HSI-MSI fusion.
arXiv Detail & Related papers (2023-10-11T07:30:37Z) - DCN-T: Dual Context Network with Transformer for Hyperspectral Image
Classification [109.09061514799413]
Hyperspectral image (HSI) classification is challenging due to spatial variability caused by complex imaging conditions.
We propose a tri-spectral image generation pipeline that transforms HSI into high-quality tri-spectral images.
Our proposed method outperforms state-of-the-art methods for HSI classification.
arXiv Detail & Related papers (2023-04-19T18:32:52Z) - Masked Spatial-Spectral Autoencoders Are Excellent Hyperspectral
Defenders [15.839321488352535]
We propose a masked spatial-spectral autoencoder (MSSA) for enhancing the robustness of HSI analysis systems.
To improve the defense transferability and address the problem of limited labelled samples, MSSA employs spectra reconstruction as a pretext task.
Comprehensive experiments over three benchmarks verify the effectiveness of MSSA in comparison with the state-of-the-art hyperspectral classification methods.
arXiv Detail & Related papers (2022-07-16T01:33:13Z) - Hyperspectral Image Segmentation based on Graph Processing over
Multilayer Networks [51.15952040322895]
One important task of hyperspectral image (HSI) processing is the extraction of spectral-spatial features.
We propose several approaches to HSI segmentation based on M-GSP feature extraction.
Our experimental results demonstrate the strength of M-GSP in HSI processing and spectral-spatial information extraction.
arXiv Detail & Related papers (2021-11-29T23:28:18Z) - Large-Scale Hyperspectral Image Clustering Using Contrastive Learning [18.473767002905433]
We present a scalable deep online clustering model, named Spectral-Spatial Contrastive Clustering (SSCC)
We exploit a symmetric twin neural network comprised of a projection head with a dimensionality of the cluster number to conduct dual contrastive learning from a spectral-spatial augmentation pool.
The resulting approach is trained in an end-to-end fashion by batch-wise optimization, making it robust in large-scale data and resulting in good generalization ability for unseen data.
arXiv Detail & Related papers (2021-11-15T17:50:06Z) - Spectral Splitting and Aggregation Network for Hyperspectral Face
Super-Resolution [82.59267937569213]
High-resolution (HR) hyperspectral face image plays an important role in face related computer vision tasks under uncontrolled conditions.
In this paper, we investigate how to adapt the deep learning techniques to hyperspectral face image super-resolution.
We present a spectral splitting and aggregation network (SSANet) for HFSR with limited training samples.
arXiv Detail & Related papers (2021-08-31T02:13:00Z) - Spectral Analysis Network for Deep Representation Learning and Image
Clustering [53.415803942270685]
This paper proposes a new network structure for unsupervised deep representation learning based on spectral analysis.
It can identify the local similarities among images in patch level and thus more robust against occlusion.
It can learn more clustering-friendly representations and is capable to reveal the deep correlations among data samples.
arXiv Detail & Related papers (2020-09-11T05:07:15Z) - Agglomerative Neural Networks for Multi-view Clustering [109.55325971050154]
We propose the agglomerative analysis to approximate the optimal consensus view.
We present Agglomerative Neural Network (ANN) based on Constrained Laplacian Rank to cluster multi-view data directly.
Our evaluations against several state-of-the-art multi-view clustering approaches on four popular datasets show the promising view-consensus analysis ability of ANN.
arXiv Detail & Related papers (2020-05-12T05:39:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.