Image Segmentation Using Deep Learning: A Survey

@article{Minaee2021ImageSU,
  title={Image Segmentation Using Deep Learning: A Survey},
  author={Shervin Minaee and Yuri Boykov and Fatih Murat Porikli and Antonio J. Plaza and Nasser Kehtarnavaz and Demetri Terzopoulos},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  year={2021},
  volume={PP}
}
Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among others, and numerous segmentation algorithms are found in the literature. Against this backdrop, the broad success of Deep Learning (DL) has prompted the development of new image segmentation approaches leveraging DL models. We provide a comprehensive… 
View on PubMed
arxiv.org
474 Citations
Highly Influential Citations
13
Background Citations
217
Methods Citations
93
Results Citations
2

474 Citations

Citation Type

Citation Type

Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation
TLDR
This thesis proposes an end-to-end trainable image segmentation framework that unifies CNNs and active contour models with learnable parameters for fast and robust object delineation, and a novel approach for disentangling edge and texture processing in segmentation networks.
Medical Image Segmentation With Limited Supervision: A Review of Deep Network Models
TLDR
A systematic and up-to-date review of the solutions above, with summaries and comments about the methodologies, and highlights several problems in this field.
Comparison of Deep-Learning-Based Segmentation Models: Using Top View Person Images
TLDR
This work explores widely used deep learning-based models for person segmentation using top view data set using Fully Convolutional Neural Network with Resnet-101 architecture, U-Net with Encoder-Decoder architecture, and a DeepLabV3 model with encoder-decoder architecture.
PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation
TLDR
A high-efficient development toolkit for image segmentation, named PaddleSeg, which aims to help both developers and researchers in the whole process of designing segmentation models, training models, optimizing performance and inference speed, and deploying models.
Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation
TLDR
This work compares some variant of the DeepLab architecture obtained by varying the decoder backbone and compares several decoder architectures, including ResNet, Xception, EfficentNet, MobileNet and perturb their layers by substituting ReLU activation layers with other functions to create deep ensembles shown to be very effective.
PMED-Net: Pyramid Based Multi-Scale Encoder-Decoder Network for Medical Image Segmentation
TLDR
A pyramidical multi-scale encoder-decoder network, namely PMED-Net, is proposed for medical image segmentation, and the experimental results are either better or on par with other state-of-the-art networks in terms of IoU, F1-Score, and sensitivity metrics.
Variability and reproducibility in deep learning for medical image segmentation
TLDR
This article proposes an original overview of the sources of variability to better understand the challenges and issues of reproducibility related to deep learning for medical image segmentation and proposes 3 main recommendations to address potential issues.
Binary segmentation of medical images using implicit spline representations and deep learning
Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning
TLDR
A novel DRL agent designed to imitate the human process to perform LV segmentation and achieves higher F-measure accuracy compared with deep learning methods when training with a very limited number of samples.
Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends
TLDR
An overview of the evolution of DL with a focus on image segmentation and object detection in convolutional neural networks (CNN) starts in 2012, when a CNN set new standards in image recognition, and lasts until late 2019.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 207 REFERENCES
Unsupervised urban scene segmentation via domain adaptation
Medical Image Segmentation Using Deep Learning: A Survey
TLDR
A comprehensive thematic survey on medical image segmentation using deep learning techniques, without including unsupervised approaches since they have been introduced in many old surveys and they are not popular currently.
Cell Image Segmentation Using Generative Adversarial Networks, Transfer Learning, and Augmentations
  • M. Majurski, P. Manescu, P. Bajcsy
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2019
TLDR
This goal is to compare the accuracy gains of CNN-based segmentation by using un-annotated images via Generative Adversarial Networks (GAN), annotated out-of-bio-domain images via transfer learning, and a priori knowledge about microscope imaging mapped into geometric augmentations of a small collection of annotated images.
W-Net: A Deep Model for Fully Unsupervised Image Segmentation
TLDR
This paper revisits the problem of purely unsupervised image segmentation and proposes a novel deep architecture for this problem by concatenating two fully convolutional networks together into an autoencoder--one for encoding and one for decoding.
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
TLDR
This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.
Scene labeling with LSTM recurrent neural networks
TLDR
The approach, which has a much lower computational complexity than prior methods, achieved state-of-the-art performance over the Stanford Background and the SIFT Flow datasets and the ability to visualize feature maps from each layer supports the hypothesis that LSTM networks are overall suited for image processing tasks.
Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network
TLDR
This work presents a novel deep learning method for unsupervised segmentation of blood vessels, inspired by the field of active contours and introduces a new loss term, which is based on the morphological Active Contours Without Edges (ACWE) optimization method.
Learning Active Contour Models for Medical Image Segmentation
TLDR
A new loss function which incorporates area and size information and integrates this into a dense deep learning model is proposed which outperforms other mainstream loss function Cross-entropy on two common segmentation networks.
Ladder-Style DenseNets for Semantic Segmentation of Large Natural Images
TLDR
A DenseNet-based ladder-style architecture is proposed which is able to deliver high modelling power with very lean representations at the original resolution, allow training at megapixel resolution on commodity hardware and display fair semantic segmentation performance even without ImageNet pre-training.
SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation
TLDR
A novel end-to-end adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local features that capture long- and short-range spatial relationships between pixels is proposed.
...
1
2
3
4
5
...