scholarly journals Representation Learning Based on Autoencoder and Deep Adaptive Clustering for Image Clustering

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Siquan Yu ◽  
Jiaxin Liu ◽  
Zhi Han ◽  
Yong Li ◽  
Yandong Tang ◽  
...  
Keyword(s):  
Local Structure ◽  
Image Representation ◽  
Representation Learning ◽  
Classification Problem ◽  
Image Clustering ◽  
Clustering Methods ◽  
Adaptive Clustering ◽  
Complex Procedure ◽  
Convolutional Autoencoder ◽  
Image Representations

Image clustering is a complex procedure, which is significantly affected by the choice of image representation. Most of the existing image clustering methods treat representation learning and clustering separately, which usually bring two problems. On the one hand, image representations are difficult to select and the learned representations are not suitable for clustering. On the other hand, they inevitably involve some clustering step, which may bring some error and hurt the clustering results. To tackle these problems, we present a new clustering method that efficiently builds an image representation and precisely discovers cluster assignments. For this purpose, the image clustering task is regarded as a binary pairwise classification problem with local structure preservation. Specifically, we propose here such an approach for image clustering based on a fully convolutional autoencoder and deep adaptive clustering (DAC). To extract the essential representation and maintain the local structure, a fully convolutional autoencoder is applied. To manipulate feature to clustering space and obtain a suitable image representation, the DAC algorithm participates in the training of autoencoder. Our method can learn an image representation that is suitable for clustering and discover the precise clustering label for each image. A series of real-world image clustering experiments verify the effectiveness of the proposed algorithm.

scholarly journals A Hybrid Autoencoder Network for Unsupervised Image Clustering

Algorithms ◽  
2019 ◽  
Vol 12 (6) ◽  
pp. 122 ◽  
Author(s):  
Pei-Yin Chen ◽  
Jih-Jeng Huang
Keyword(s):  
Feature Learning ◽  
Image Data ◽  
Image Clustering ◽  
Great Success ◽  
Distance Metrics ◽  
Clustering Methods ◽  
Unsupervised Feature Learning ◽  
Agglomerative Clustering ◽  
Convolutional Autoencoder ◽  
Important Field

Image clustering involves the process of mapping an archive image into a cluster such that the set of clusters has the same information. It is an important field of machine learning and computer vision. While traditional clustering methods, such as k-means or the agglomerative clustering method, have been widely used for the task of clustering, it is difficult for them to handle image data due to having no predefined distance metrics and high dimensionality. Recently, deep unsupervised feature learning methods, such as the autoencoder (AE), have been employed for image clustering with great success. However, each model has its specialty and advantages for image clustering. Hence, we combine three AE-based models—the convolutional autoencoder (CAE), adversarial autoencoder (AAE), and stacked autoencoder (SAE)—to form a hybrid autoencoder (BAE) model for image clustering. The MNIST and CIFAR-10 datasets are used to test the result of the proposed models and compare the results with others. The results of the clustering criteria indicate that the proposed models outperform others in the numerical experiment.

scholarly journals Fi-Fo Detector: Figure and Formula Detection Using Deformable Networks

2020 ◽  
Vol 10 (18) ◽  
pp. 6460
Author(s):  
Junaid Younas ◽  
Shoaib Ahmed Siddiqui ◽  
Mohsin Munir ◽  
Muhammad Imran Malik ◽  
Faisal Shafait ◽  
...  
Keyword(s):  
Computer Vision ◽  
Image Representation ◽  
Hybrid Approach ◽  
Representation Learning ◽  
Superior Performance ◽  
Document Images ◽  
Connected Component ◽  
Study Results ◽  
Image Representations ◽  
Ablation Study

We propose a novel hybrid approach that fuses traditional computer vision techniques with deep learning models to detect figures and formulas from document images. The proposed approach first fuses the different computer vision based image representations, i.e., color transform, connected component analysis, and distance transform, termed as Fi-Fo image representation. The Fi-Fo image representation is then fed to deep models for further refined representation-learning for detecting figures and formulas from document images. The proposed approach is evaluated on a publicly available ICDAR-2017 Page Object Detection (POD) dataset and its corrected version. It produces the state-of-the-art results for formula and figure detection in document images with an f1-score of 0.954 and 0.922, respectively. Ablation study results reveal that the Fi-Fo image representation helps in achieving superior performance in comparison to raw image representation. Results also establish that the hybrid approach helps deep models to learn more discriminating and refined features.

scholarly journals Convolutional Neural Networks with Transfer Learning for Recognition of COVID-19: A Comparative Study of Different Approaches

AI ◽  
2020 ◽  
Vol 1 (4) ◽  
pp. 586-606
Author(s):  
Tanmay Garg ◽  
Mamta Garg ◽  
Om Prakash Mahela ◽  
Akhil Ranjan Garg
Keyword(s):  
Neural Networks ◽  
Principal Component Analysis ◽  
Feature Selection ◽  
Convolutional Neural Networks ◽  
Image Representation ◽  
Principal Component ◽  
Classification Problem ◽  
The Other ◽  
X Ray ◽  
Image Representations

To judge the ability of convolutional neural networks (CNNs) to effectively and efficiently transfer image representations learned on the ImageNet dataset to the task of recognizing COVID-19 in this work, we propose and analyze four approaches. For this purpose, we use VGG16, ResNetV2, InceptionResNetV2, DenseNet121, and MobileNetV2 CNN models pre-trained on ImageNet dataset to extract features from X-ray images of COVID and Non-COVID patients. Simulations study performed by us reveal that these pre-trained models have a different level of ability to transfer image representation. We find that in the approaches that we have proposed, if we use either ResNetV2 or DenseNet121 to extract features, then the performance of these approaches to detect COVID-19 is better. One of the important findings of our study is that the use of principal component analysis for feature selection improves efficiency. The approach using the fusion of features outperforms all the other approaches, and with this approach, we could achieve an accuracy of 0.94 for a three-class classification problem. This work will not only be useful for COVID-19 detection but also for any domain with small datasets.

scholarly journals Surface Reconstruction Using Adaptive Clustering Methods

2001 ◽  
pp. 199-218 ◽  
Author(s):  
B. Heckel ◽  
A. E. Uva ◽  
B. Hamann ◽  
K. I. Joy
Keyword(s):  
Surface Reconstruction ◽  
Clustering Methods ◽  
Adaptive Clustering

scholarly journals A TWO-CHANNEL MODEL FOR REPRESENTATION LEARNING IN VIETNAMESE SENTIMENT CLASSIFICATION PROBLEM

2020 ◽  
Vol 36 (4) ◽  
pp. 305-323
Author(s):  
Quan Hoang Nguyen ◽  
Ly Vu ◽  
Quang Uy Nguyen
Keyword(s):  
Channel Model ◽  
Rapid Development ◽  
Representation Learning ◽  
Classification Problem ◽  
Sentiment Classification ◽  
Complex Sentences ◽  
Digital World ◽  
Part Of Speech ◽  
Proposed Model ◽  
Important Research Topic

Sentiment classification (SC) aims to determine whether a document conveys a positive or negative opinion. Due to the rapid development of the digital world, SC has become an important research topic that affects many aspects of our life. In SC based on machine learning, the representation of the document strongly influences on its accuracy. Word Embedding (WE)-based techniques, i.e., Word2vec techniques, are proved to be beneficial techniques to the SC problem. However, Word2vec is often not enough to represent the semantic of documents with complex sentences of Vietnamese. In this paper, we propose a new representation learning model called a \textbf{two-channel vector} to learn a higher-level feature of a document in SC. Our model uses two neural networks to learn the semantic feature, i.e., Word2vec and the syntactic feature, i.e., Part of Speech tag (POS). Two features are then combined and input to a \textit{Softmax} function to make the final classification. We carry out intensive experiments on $4$ recent Vietnamese sentiment datasets to evaluate the performance of the proposed architecture. The experimental results demonstrate that the proposed model can significantly enhance the accuracy of SC problems compared to two single models and a state-of-the-art ensemble method.

scholarly journals Enhanced Affinity for Spectral Clustering using Topological Node Features (TNFS)

2019 ◽  
Vol 9 (1) ◽  
pp. 974-987
Keyword(s):  
Local Structure ◽  
Data Clustering ◽  
Spectral Clustering ◽  
Clustering Coefficient ◽  
Complex Data ◽  
Clustering Methods ◽  
Pairwise Similarity ◽  
Synthetic Datasets ◽  
Summation Index ◽  
Affinity Measure

Data clustering is an active topic of research as it has applications in various fields such as biology, management, statistics, pattern recognition, etc. Spectral Clustering (SC) has gained popularity in recent times due to its ability to handle complex data and ease of implementation. A crucial step in spectral clustering is the construction of the affinity matrix, which is based on a pairwise similarity measure. The varied characteristics of datasets affect the performance of a spectral clustering technique. In this paper, we have proposed an affinity measure based on Topological Node Features (TNFs) viz., Clustering Coefficient (CC) and Summation index (SI) to define the notion of density and local structure. It has been shown that these features improve the performance of SC in clustering the data. The experiments were conducted on synthetic datasets, UCI datasets, and the MNIST handwritten datasets. The results show that the proposed affinity metric outperforms several recent spectral clustering methods in terms of accuracy.

Convolutional Autoencoder for Unsupervised Representation Learning of PolSAR Time-Series

2021 ◽  
Author(s):  
Thomas Di Martino ◽  
Regis Guinvarc'h ◽  
Laetitia Thirion-Lefevre ◽  
Elise Colin Koeniguer
Keyword(s):  
Time Series ◽  
Representation Learning ◽  
Convolutional Autoencoder

Pattern Mining and Clustering on Image Databases

2008 ◽  
pp. 187-212
Author(s):  
Marinette Bouet ◽  
Pierre Gançarski ◽  
Marie-Aude Aufaure ◽  
Omar Boussaïd
Keyword(s):  
Pattern Mining ◽  
Frequent Pattern Mining ◽  
Image Data ◽  
Research Direction ◽  
Relevant Information ◽  
Frequent Pattern ◽  
Image Clustering ◽  
Image Mining ◽  
Clustering Methods ◽  
New Research

Analysing and mining image data to derive potentially useful information is a very challenging task. Image mining concerns the extraction of implicit knowledge, image data relationships, associations between image data and other data or patterns not explicitly stored in the images. Another crucial task is to organize the large image volumes to extract relevant information. In fact, decision support systems are evolving to store and analyse these complex data. This paper presents a survey of the relevant research related to image data processing. We present data warehouse advances that organize large volumes of data linked with images and then, we focus on two techniques largely used in image mining. We present clustering methods applied to image analysis and we introduce the new research direction concerning pattern mining from large collections of images. While considerable advances have been made in image clustering, there is little research dealing with image frequent pattern mining. We shall try to understand why.

Sign in / Sign up

Export Citation Format

Share Document