<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Deep learning methods, used in machine vision challenges, often face the problem of the amount and quality of data. To address this issue, we investigate the transfer learning method. In this study, we briefly describe the idea and introduce two main strategies of transfer learning. We also present the widely-used neural network models, that in recent years performed best in ImageNet classification challenges. Furthermore, we shortly describe three different experiments from computer vision field, that confirm the developed algorithms ability to classify images with overall accuracy 87.2-95%. Achieved numbers are state-of-the-art results in melanoma thickness prediction, anomaly detection and <italic>Clostridium di cile</italic> cytotoxicity classification problems.</p></abstract>

Deep learning methods, used in machine vision challenges, often face the problem of the amount and quality of data. To address this issue, we investigate the transfer learning method. In this study, we briefly describe the idea and introduce two main strategies of transfer learning. We also present the widely-used neural network models, that in recent years performed best in ImageNet classification challenges. Furthermore, we shortly describe three different experiments from computer vision field, that confirm the developed algorithms ability to classify images with overall accuracy 87.2-95%. Achieved numbers are state-of-the-art results in melanoma thickness prediction, anomaly detection and Clostridium di cile cytotoxicity classification problems.

Transfer Learning Methods as a New Approach in Computer Vision Tasks with Small Datasets

Department of Automatic Control and Robotics

Foundations of Computing and Decision Sciences

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Deep learning methods, used in machine vision challenges, often face the problem of the amount and quality of data. To address this issue, we investigate the...

Transfer Learning Methods as a New Approach in Computer Vision Tasks with Small Datasets

Pubblicato online: 18 set 2020

Pagine: 179 - 193

Ricevuto: 29 feb 2020

Accettato: 29 lug 2020

DOI: https://doi.org/10.2478/fcds-2020-0010

Parole chiave
Deep neural networks, Transfer learning, Signal processing, Image analysis, Anomaly detection

© 2020 Andrzej Brodzicki et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Transfer Learning Methods as a New Approach in Computer Vision Tasks with Small Datasets

Pubblicato online: 18 set 2020

Pagine: 179 - 193

Ricevuto: 29 feb 2020

Accettato: 29 lug 2020

DOI: https://doi.org/10.2478/fcds-2020-0010

Parole chiaveDeep neural networks, Transfer learning, Signal processing, Image analysis, Anomaly detection

© 2020 Andrzej Brodzicki et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Parole chiave
Deep neural networks, Transfer learning, Signal processing, Image analysis, Anomaly detection