2022
DOI: 10.1080/08839514.2022.2032924
|View full text |Cite
|
Sign up to set email alerts
|

A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D Images

Abstract: Semantic segmentation is the pixel-wise labelling of an image. Since the problem is defined at the pixel level, determining image class labels only is not acceptable, but localising them at the original image pixel resolution is necessary. Boosted by the extraordinary ability of convolutional neural networks (CNN) in creating semantic, high level and hierarchical image features; excessive numbers of deep learning-based 2D semantic segmentation approaches have been proposed within the last decade. In this surve… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
45
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
3
2

Relationship

0
10

Authors

Journals

citations
Cited by 124 publications
(46 citation statements)
references
References 176 publications
0
45
0
1
Order By: Relevance
“…The refined extraction task of the marine raft aquaculture area aims to identify all of the pixels belonging to marine raft aquaculture areas in the image and locate their positions to serve the subsequent statistics of aquaculture area and estimation of aquaculture production. This task belongs to the full-pixel semantic segmentation problem in the field of computer vision [29][30][31][32]. As popular semantic segmentation models, FCN [33], Unet [34], PSPnet [35] and DeepLabV3+ [36] each have their own advantages.…”
Section: Comparison and Selection Of Models For Semantic Segmentationmentioning
confidence: 99%
“…The refined extraction task of the marine raft aquaculture area aims to identify all of the pixels belonging to marine raft aquaculture areas in the image and locate their positions to serve the subsequent statistics of aquaculture area and estimation of aquaculture production. This task belongs to the full-pixel semantic segmentation problem in the field of computer vision [29][30][31][32]. As popular semantic segmentation models, FCN [33], Unet [34], PSPnet [35] and DeepLabV3+ [36] each have their own advantages.…”
Section: Comparison and Selection Of Models For Semantic Segmentationmentioning
confidence: 99%
“…The training batch sizes for DeepLabV3+ Xception were 8 while the rest of models had batch size 4. We use pixel accuracy (PixAcc) [39] and mean intersection-of-union (mIoU) [40] to compare model performances.…”
Section: Spacecraft Instance Segmentationmentioning
confidence: 99%
“…Many different methods have been developed to solve this problem: FCN [6], U-Net [7], SegNet [8], among others. In recent years, many models have significantly improved the quality of semantic segmentation [9], [10].…”
Section: Introductionmentioning
confidence: 99%