Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images

Numerous methods have been proposed for semantic segmentation and the state-of-the-art part is likely to be incorporated by deep learning-based methods which show a salient performance. This study addresses the challenge of semantic segmentation in low-contrast imbalanced underwater images. Moreover...

Full description

Saved in:
Bibliographic Details
Main Author: Jale Bektaş
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/24/11964
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850240099623632896
author Jale Bektaş
author_facet Jale Bektaş
author_sort Jale Bektaş
collection DOAJ
description Numerous methods have been proposed for semantic segmentation and the state-of-the-art part is likely to be incorporated by deep learning-based methods which show a salient performance. This study addresses the challenge of semantic segmentation in low-contrast imbalanced underwater images. Moreover, it employs nine model fusions as a downstream workflow task using encoder–decoder architectures with Dice Loss and Focal Loss training focusing on the imbalance data. Afterwards, the most effective two encoder–decoder fusion models, Res34+Unet and VGG19+FPN, by 0.592%, 0.590% mIoU on average and by 0.510%, 0.491% F1-score yielded better performance, respectively, than other models. Using a weight-optimization algorithm, the ensemble model with recreated IoU results improves the accuracy for both the Res34+Unet and the VGG19+FPN models, by 0.652% mIoU on average which is 6%. The ensemble model combines the model performances of independent models by considering their superior inference accuracy on a per-class basis separately and improves the model performances by emphasizing the better one on a per-class basis.
format Article
id doaj-art-cdede0e443184f07b354d5b6aec94d59
institution OA Journals
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-cdede0e443184f07b354d5b6aec94d592025-08-20T02:00:56ZengMDPI AGApplied Sciences2076-34172024-12-0114241196410.3390/app142411964Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater ImagesJale Bektaş0Department of Computer Engineering, Mersin University, 33110 Mersin, TürkiyeNumerous methods have been proposed for semantic segmentation and the state-of-the-art part is likely to be incorporated by deep learning-based methods which show a salient performance. This study addresses the challenge of semantic segmentation in low-contrast imbalanced underwater images. Moreover, it employs nine model fusions as a downstream workflow task using encoder–decoder architectures with Dice Loss and Focal Loss training focusing on the imbalance data. Afterwards, the most effective two encoder–decoder fusion models, Res34+Unet and VGG19+FPN, by 0.592%, 0.590% mIoU on average and by 0.510%, 0.491% F1-score yielded better performance, respectively, than other models. Using a weight-optimization algorithm, the ensemble model with recreated IoU results improves the accuracy for both the Res34+Unet and the VGG19+FPN models, by 0.652% mIoU on average which is 6%. The ensemble model combines the model performances of independent models by considering their superior inference accuracy on a per-class basis separately and improves the model performances by emphasizing the better one on a per-class basis.https://www.mdpi.com/2076-3417/14/24/11964semantic segmentationencoder–decoder fusionUnetFPNLinkNetensemble model
spellingShingle Jale Bektaş
Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images
Applied Sciences
semantic segmentation
encoder–decoder fusion
Unet
FPN
LinkNet
ensemble model
title Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images
title_full Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images
title_fullStr Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images
title_full_unstemmed Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images
title_short Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images
title_sort automating an encoder decoder incorporated ensemble model semantic segmentation workflow on low contrast underwater images
topic semantic segmentation
encoder–decoder fusion
Unet
FPN
LinkNet
ensemble model
url https://www.mdpi.com/2076-3417/14/24/11964
work_keys_str_mv AT jalebektas automatinganencoderdecoderincorporatedensemblemodelsemanticsegmentationworkflowonlowcontrastunderwaterimages