DSpace Repository

A Comprehensive Study on Deep Image Classification with Small Datasets

Show simple item record

dc.contributor.author Gayani, C.
dc.contributor.author Kokul, T.
dc.contributor.author Amalka, P.
dc.date.accessioned 2020-01-08T05:03:36Z
dc.date.accessioned 2022-06-27T04:11:18Z
dc.date.available 2020-01-08T05:03:36Z
dc.date.available 2022-06-27T04:11:18Z
dc.date.issued 2019-12-17
dc.identifier.isbn 978-981-15-1289-6
dc.identifier.uri http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/1311
dc.description.abstract Convolutional Neural Networks (CNNs) showed state-of-the-art accuracyin image classification on large-scale image datasets. However, CNNs showconsiderable poor performance in classifying tiny data since their large number ofparameters over-fit the training data. We investigate the classification characteristicsof CNNs on tiny data, which are important for many practical applications. Thisstudy analyzes the performance of CNNs for direct and transfer learning-basedtraining approaches. Evaluation is performed on two publicly available benchmarkdatasets. Our study shows the accuracy change when altering the DCNN depth indirect training to indicate the optimal depth for direct training. Further, fine-tuningsource and target network with lower learning rate gives higher accuracy for tinyimage classification. en_US
dc.language.iso en en_US
dc.publisher Springer en_US
dc.subject Deep image classification en_US
dc.subject CNN en_US
dc.subject Transfer learning en_US
dc.title A Comprehensive Study on Deep Image Classification with Small Datasets en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record