A Hybrid Autoencoder Network for Unsupervised Image Clustering

Chen, Pei-Yin; Huang, Jih-Jeng

doi:10.3390/a12060122

Cited by 13 publications

(4 citation statements)

References 22 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The researchers in this paper [12] created a hybrid autoencoder (BAE) model for image clustering by combining three AE-based models: the convolutional autoencoder (CAE), adversarial autoencoder (AAE), and stacking autoencoder (SAE). The MNIST and CIFAR-10 datasets are used to test the suggested models' results and compare them to those of other researchers.…”

Section: Contributions Of Deep Clusteringmentioning

confidence: 99%

Unsupervised Deep Learning: Taxonomy and algorithms

Chefrour

Souici-Meslati

2022

IJCAI

View full text Add to dashboard Cite

Clustering is a fundamental challenge in many data-driven application fields and machine learning techniques. The data distribution determines the quality of the outcomes, which has a significant impact on clustering performance. As a result, deep neural networks can be used to learn more accurate data representations for clustering. Many recent studies have focused on employing deep neural networks to develop a clustering-friendly representation, which has resulted in a significant improvement in clustering performance. We present a systematic survey of clustering with deep learning in this study. Then, a taxonomy of deep clustering is proposed, as well as some sample algorithms for our overview. Finally, we discuss some exciting future possibilities for clustering using deep learning and offer some remarks. Povzetek: Ta članek opisuje metode globokega združevanja v skupine in predlaga taksonomijo globokega združevanja v skupine.

show abstract

Section: Contributions Of Deep Clusteringmentioning

confidence: 99%

Unsupervised Deep Learning: Taxonomy and algorithms

Chefrour

Souici-Meslati

2022

IJCAI

View full text Add to dashboard Cite

show abstract

“…The experiments represent that their work performs better from spectral clustering. Chen et al [32] design a methodology for the analysis of high dimensional image data. The new model is based on a hybrid autoencoder, which combines the Stacked AutoEncoder (SAE), Convolutional AutoEncoder (CAE), and Adversarial AutoEncoder (AAE).…”

Section: Autoencoder-based Clusteringmentioning

confidence: 99%

“…Eq. (32) shows the computation of precision. 𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 = 𝑇𝑃 𝑇𝑃+𝐹𝑃 (32) Recall: The recall is a ratio of correctly predicted positive observation and all observation of the actual class.…”

Section: Entropymentioning

confidence: 99%

Gene encoder: a feature selection technique through unsupervised deep learning-based clustering for large gene expression data

Uzma

Al-Obeidat

Tubaishat

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

Cancer is a severe condition of uncontrolled cell division that results in a tumor formation that spreads to other tissues of the body. Therefore, the development of new medication and treatment methods for this is in demand. Classification of microarray data plays a vital role in handling such situations. The relevant gene selection is an important step for the classification of microarray data. This work presents gene-encoder, an unsupervised two-stage feature selection technique for the cancer samples' classification. The first stage aggregates three filter methods, namely, Principal Component Analysis (PCA), correlation, and spectral-based feature selection techniques. Next, the Genetic Algorithm (GA) is used, which evaluates the chromosome utilizing the autoencoder-based clustering. The resultant feature subset is used for the classification task. Three classifiers, namely, Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Random Forest (RF) are used in this work to avoid the dependency on any one classifier. Six benchmark gene expression datasets are used for the performance evaluation and a comparisons is made with four state-of-the-art related algorithms. Three set of experiments are carried out to evaluate the proposed method. These experiments are for the evaluation of the selected features based on sample-based clustering, adjusting optimal parameters, and for selecting better performing classifier. The comparison is based on accuracy, recall, false-positive rate, precision, Fmeasure, and entropy. The obtained results suggest better performance of the current proposal.

show abstract

“…They obtained a practical and abstract feature, which is more informative for clustering purposes. They showed that their proposed deep network could learn a nonlinear mapping by effectively partitioning the transformed feature space [23]. Huang et al [24] proposed a deep embedded network to use a multilayer Gaussian restricted Boltzmann machine (GRBM) for feature extraction with preserving spatial locality and group sparsity constraints, enabling the model to learn more robust representations for clustering tasks.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Multi-Sensor Remote Sensing Image Clustering in Urban Areas via Boosted Convolutional Autoencoder (BCAE)

et al. 2021

View full text Add to dashboard Cite

High-resolution urban image clustering has remained a challenging task. This is mainly because its performance strongly depends on the discrimination power of features. Recently, several studies focused on unsupervised learning methods by autoencoders to learn and extract more efficient features for clustering purposes. This paper proposes a Boosted Convolutional AutoEncoder (BCAE) method based on feature learning for efficient urban image clustering. The proposed method was applied to multi-sensor remote-sensing images through a multistep workflow. The optical data were first preprocessed by applying a Minimum Noise Fraction (MNF) transformation. Then, these MNF features, in addition to the normalized Digital Surface Model (nDSM) and vegetation indexes such as Normalized Difference Vegetation Index (NDVI) and Excess Green (ExG(2)), were used as the inputs of the BCAE model. Next, our proposed convolutional autoencoder was trained to automatically encode upgraded features and boost the hand-crafted features for producing more clustering-friendly ones. Then, we employed the Mini Batch K-Means algorithm to cluster deep features. Finally, the comparative feature sets were manually designed in three modes to prove the efficiency of the proposed method in extracting compelling features. Experiments on three datasets show the efficiency of BCAE for feature learning. According to the experimental results, by applying the proposed method, the ultimate features become more suitable for clustering, and spatial correlation among the pixels in the feature learning process is also considered.

show abstract

A Hybrid Autoencoder Network for Unsupervised Image Clustering

Cited by 13 publications

References 22 publications

Unsupervised Deep Learning: Taxonomy and algorithms

Unsupervised Deep Learning: Taxonomy and algorithms

Gene encoder: a feature selection technique through unsupervised deep learning-based clustering for large gene expression data

An Efficient Multi-Sensor Remote Sensing Image Clustering in Urban Areas via Boosted Convolutional Autoencoder (BCAE)

Contact Info

Product

Resources

About