Classifying CIFAR-10 Images Using Unsupervised Feature & Ensemble Learning. Viet, T. & Gopee, N. abstract bibtex We perform the image classification task on the CIFAR-10 dataset, where each image belongs to one of the ten distinct classes. The classes are mutually exclusive and are mostly objects and animals. The images are small (32 ⇥ 32 pixels), of uniform size and shape, and RGB coloured. We implement an proposed image preprocessing framework to learn and extract the salient features of the images. The method was demonstrated to increase the classification performance significantly. We testify such claim and see a considerable improvement of more than 15% from the baseline (i.e., without preprocessing). We further experiment with various parameters and settings of the proposed method to tune the preprocessing frameworks. We also experiment with a variety of linear classifiers on the preprocessed images. We find out that a simple SVM classifier with linear kernel performs the best. We finally experiment with ensemble learning by combining a linear SVM with a multinomial logistic regression. The ensemble learning marginally improves on the simple linear SVM at a high computational cost.
@article{viet_classifying_nodate,
title = {Classifying {CIFAR}-10 {Images} {Using} {Unsupervised} {Feature} \& {Ensemble} {Learning}},
abstract = {We perform the image classification task on the CIFAR-10 dataset, where each image belongs to one of the ten distinct classes. The classes are mutually exclusive and are mostly objects and animals. The images are small (32 ⇥ 32 pixels), of uniform size and shape, and RGB coloured. We implement an proposed image preprocessing framework to learn and extract the salient features of the images. The method was demonstrated to increase the classification performance significantly. We testify such claim and see a considerable improvement of more than 15\% from the baseline (i.e., without preprocessing). We further experiment with various parameters and settings of the proposed method to tune the preprocessing frameworks. We also experiment with a variety of linear classifiers on the preprocessed images. We find out that a simple SVM classifier with linear kernel performs the best. We finally experiment with ensemble learning by combining a linear SVM with a multinomial logistic regression. The ensemble learning marginally improves on the simple linear SVM at a high computational cost.},
language = {en},
author = {Viet, Truc and Gopee, Naassih},
pages = {5},
}
Downloads: 0
{"_id":"xffRLrLZXtE5kiZyo","bibbaseid":"viet-gopee-classifyingcifar10imagesusingunsupervisedfeatureensemblelearning","author_short":["Viet, T.","Gopee, N."],"bibdata":{"bibtype":"article","type":"article","title":"Classifying CIFAR-10 Images Using Unsupervised Feature & Ensemble Learning","abstract":"We perform the image classification task on the CIFAR-10 dataset, where each image belongs to one of the ten distinct classes. The classes are mutually exclusive and are mostly objects and animals. The images are small (32 ⇥ 32 pixels), of uniform size and shape, and RGB coloured. We implement an proposed image preprocessing framework to learn and extract the salient features of the images. The method was demonstrated to increase the classification performance significantly. We testify such claim and see a considerable improvement of more than 15% from the baseline (i.e., without preprocessing). We further experiment with various parameters and settings of the proposed method to tune the preprocessing frameworks. We also experiment with a variety of linear classifiers on the preprocessed images. We find out that a simple SVM classifier with linear kernel performs the best. We finally experiment with ensemble learning by combining a linear SVM with a multinomial logistic regression. The ensemble learning marginally improves on the simple linear SVM at a high computational cost.","language":"en","author":[{"propositions":[],"lastnames":["Viet"],"firstnames":["Truc"],"suffixes":[]},{"propositions":[],"lastnames":["Gopee"],"firstnames":["Naassih"],"suffixes":[]}],"pages":"5","bibtex":"@article{viet_classifying_nodate,\n\ttitle = {Classifying {CIFAR}-10 {Images} {Using} {Unsupervised} {Feature} \\& {Ensemble} {Learning}},\n\tabstract = {We perform the image classification task on the CIFAR-10 dataset, where each image belongs to one of the ten distinct classes. The classes are mutually exclusive and are mostly objects and animals. The images are small (32 ⇥ 32 pixels), of uniform size and shape, and RGB coloured. We implement an proposed image preprocessing framework to learn and extract the salient features of the images. The method was demonstrated to increase the classification performance significantly. We testify such claim and see a considerable improvement of more than 15\\% from the baseline (i.e., without preprocessing). We further experiment with various parameters and settings of the proposed method to tune the preprocessing frameworks. We also experiment with a variety of linear classifiers on the preprocessed images. We find out that a simple SVM classifier with linear kernel performs the best. We finally experiment with ensemble learning by combining a linear SVM with a multinomial logistic regression. The ensemble learning marginally improves on the simple linear SVM at a high computational cost.},\n\tlanguage = {en},\n\tauthor = {Viet, Truc and Gopee, Naassih},\n\tpages = {5},\n}\n\n","author_short":["Viet, T.","Gopee, N."],"key":"viet_classifying_nodate","id":"viet_classifying_nodate","bibbaseid":"viet-gopee-classifyingcifar10imagesusingunsupervisedfeatureensemblelearning","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mxmplx","dataSources":["aXmRAq63YsH7a3ufx"],"keywords":[],"search_terms":["classifying","cifar","images","using","unsupervised","feature","ensemble","learning","viet","gopee"],"title":"Classifying CIFAR-10 Images Using Unsupervised Feature & Ensemble Learning","year":null}