Naslov
Application of Transfer Learning for Fine-Grained Vessel Classification Using a Limited Dataset

Autori
Miličević, Mario ; Žubrinić, Krunoslav ; Obradović, Ines ; Sjekavica, Tomo

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers (APSAC2018) / - Cham : Springer, 2018, 125-131

ISBN
978-3-030-21507-1

Skup
3rd International Conference on Applied Physics, System Science and Computers (APSAC 2018)

Mjesto i datum
Dubrovnik, Hrvatska, 26.09.2018. - 28.09.2018

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
deep convolutional neural networks ; deep learning ; classification ; transfer learning ; parameter fine-tuning

Sažetak
The automatic classification of maritime vessel type from low resolution images is a significant challenge and continues to attract increasing interest because of its importance to maritime surveillance. Convolutional neural networks are the method of choice for supervised image classification, but they require a large number of annotated samples, which prevents many superior models being applied to problems with a limited number of training samples. One possible solution is transfer learning where pre-trained models are used on entirely new predictive modeling, transferring knowledge between related source and target domains. Our experimental results demonstrate that a combination of data augmentation and transfer learning leads to a better performance in the presence of small training dataset, even in the a fine-grained classification context.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA