Skip to main content

Improved Attentive Pairwise Interaction (API-Net) for Fine-Grained Image Classification.

Yet, O.Z., Rassem, T. H., Rahman, M.A. and Rahman, M.M., 2021. Improved Attentive Pairwise Interaction (API-Net) for Fine-Grained Image Classification. In: ETCCE 2021: Emerging Technology in Computing, Communication and Electronics, 21-23 December 2021, Virtual.

Full text available as:

[img]
Preview
PDF
Yet_et_al_Improved_attentive_2021.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

1MB

Official URL: https://ritechs.org/ETCCE2021/

DOI: 10.1109/ETCCE54784.2021.9689910

Abstract

Fine-grained classification is a challenging problem as one has to deal with a similar class of objects but with various types of variations. For more elaboration, they are almost similar and have subtle differences, and are confusing. In this study, aircraft will be the fine-grained object to be focused on. Aircraft which has almost similar shapes and patterns can be hardly recognized even for humans, especially those who haven not gone through any training. In recent years, a lot of proposed methods addressed to solve the difficulties in fine-grained problems by learning contrastive clues from an image. This study aims to increase the accuracy of the Attentive Pairwise Interaction Network (API-Net) by introducing data augmentation into the network structure. Some of the previous studies proved that data augmentation does help improve a network. So, this study is going to modify the API-Net with different data augmentation settings. In this study, various settings have been introduced to the API-Net. Several experiments had been done with a simple modification where a portion of the train dataset's images will randomly convert into greyscale images. These settings are, only brightness & contrast 0.2, only grayscale 0.3, only grayscale 0.5, brightness & contrast 0.2 with grayscale 0.3, and brightness & contrast 0.2 with grayscale 0.5. As a result, the proposed modification achieved with 92.74% with brightness & contrast 0.2, 92.80% on brightness & contrast 0.2 with grayscale 0.5, and 92.86% on brightness & contrast 0.2 with grayscale 0.3. While grayscale 0.3 alone achieve 93.25% and grayscale 0.5 alone achieve 93.46% compared with the original results which reached 92.77%.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Funding Agency: 10.13039/501100005605-Universiti Malaysia Pahang
Uncontrolled Keywords:Training , Shape; Brightness; Gray-scale; Pattern recognition; Aircraft; Image classification
Group:Faculty of Science & Technology
ID Code:37432
Deposited By: Symplectic RT2
Deposited On:05 Sep 2022 10:58
Last Modified:05 Sep 2022 10:58

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -