A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets
Deep convolutional neural networks have shown remarkable performance in the image classification domain. However, Deep Learning models are vulnerable to noise and redundant information encapsulated into the high-dimensional raw input images, leading to unstable and unreliable predictions. Autoencode...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7731 |
| _version_ | 1797508440068718592 |
|---|---|
| author | Emmanuel Pintelas Ioannis E. Livieris Panagiotis E. Pintelas |
| author_facet | Emmanuel Pintelas Ioannis E. Livieris Panagiotis E. Pintelas |
| author_sort | Emmanuel Pintelas |
| collection | DOAJ |
| description | Deep convolutional neural networks have shown remarkable performance in the image classification domain. However, Deep Learning models are vulnerable to noise and redundant information encapsulated into the high-dimensional raw input images, leading to unstable and unreliable predictions. Autoencoders constitute an unsupervised dimensionality reduction technique, proven to filter out noise and redundant information and create robust and stable feature representations. In this work, in order to resolve the problem of DL models’ vulnerability, we propose a convolutional autoencoder topological model for compressing and filtering out noise and redundant information from initial high dimensionality input images and then feeding this compressed output into convolutional neural networks. Our results reveal the efficiency of the proposed approach, leading to a significant performance improvement compared to Deep Learning models trained with the initial raw images. |
| first_indexed | 2024-03-10T05:04:05Z |
| format | Article |
| id | doaj.art-5dd1ec8af35a4523a22dd4d2f89657f0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:04:05Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5dd1ec8af35a4523a22dd4d2f89657f02023-11-23T01:28:50ZengMDPI AGSensors1424-82202021-11-012122773110.3390/s21227731A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image DatasetsEmmanuel Pintelas0Ioannis E. Livieris1Panagiotis E. Pintelas2Department of Mathematics, University of Patras, 26500 Patras, GreeceCore Innovation and Technology O.E., 11745 Athens, GreeceDepartment of Mathematics, University of Patras, 26500 Patras, GreeceDeep convolutional neural networks have shown remarkable performance in the image classification domain. However, Deep Learning models are vulnerable to noise and redundant information encapsulated into the high-dimensional raw input images, leading to unstable and unreliable predictions. Autoencoders constitute an unsupervised dimensionality reduction technique, proven to filter out noise and redundant information and create robust and stable feature representations. In this work, in order to resolve the problem of DL models’ vulnerability, we propose a convolutional autoencoder topological model for compressing and filtering out noise and redundant information from initial high dimensionality input images and then feeding this compressed output into convolutional neural networks. Our results reveal the efficiency of the proposed approach, leading to a significant performance improvement compared to Deep Learning models trained with the initial raw images.https://www.mdpi.com/1424-8220/21/22/7731convolutional autoencodersdimensionality reductiondeep learningconvolutional neural networkscomputer visionimage classification |
| spellingShingle | Emmanuel Pintelas Ioannis E. Livieris Panagiotis E. Pintelas A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets Sensors convolutional autoencoders dimensionality reduction deep learning convolutional neural networks computer vision image classification |
| title | A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets |
| title_full | A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets |
| title_fullStr | A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets |
| title_full_unstemmed | A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets |
| title_short | A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets |
| title_sort | convolutional autoencoder topology for classification in high dimensional noisy image datasets |
| topic | convolutional autoencoders dimensionality reduction deep learning convolutional neural networks computer vision image classification |
| url | https://www.mdpi.com/1424-8220/21/22/7731 |
| work_keys_str_mv | AT emmanuelpintelas aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT ioanniselivieris aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT panagiotisepintelas aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT emmanuelpintelas convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT ioanniselivieris convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT panagiotisepintelas convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets |