In the digital era, image segmentation is regarded as an indispensible task of computer vision, and its applications range from an autonomous car driving to medical diagnosis. Due to the huge success of deep learning models in a broad range of computer vision applications, there have been enormous research scopes investigating image segmentation using deep learning models.
   More advanced image segmentation approaches are empowered by deep learning technology. Several deep learning architectures utilized for image segmentation are Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), Ensemble learning, DeepLab, and SegNet neural network. Some notable application scenarios of deep learning-based image segmentation are medical image analysis, object detection, image retrieval, remote sensing, robotic perception, video surveillance, and augmented reality.
   Convolutional Models With Graphical Models, Encoder-Decoder Based Models, Multi-Scale and Pyramid Network Based Models, Regional Convolutional Neural Network (R-CNN) Based Models, Dilated Convolutional Models and DeepLab Family, Recurrent Neural Network Based Models, Attention-Based Models, Generative Models, and Adversarial Training, CNN Models With Active Contour Models are some of the advanced deep learning models utilized for image segmentation.
   Even though deep learning models are effectively applied for image segmentation tasks, some challenges appear in such models. Thus more research efforts are needed. The most promising future research scopes of deep learning-based image segmentation are Real-time Models for Various Applications, Interpretable Deep Models, Weakly-Supervised and Unsupervised Learning, Efficient Memory Models, and 3D Point-Cloud Segmentation.
   Several studies and surveys of deep learning-enabled image segmentation were published recently that discuss deep learning models overview, strengths, challenges, remarkable image segmentation datasets, performances, challenges, opportunities, and future research directions. Such surveys and their application-specific surveys are listed below: