A Survey on Image Semantic Segmentation Using Deep Learning Techniques

Cheng, Jieren; Li, Hua; Li, Dengbo; Hua, Shuai; Sheng, Victor S.

doi:10.32604/cmc.2023.032757

Cited by 8 publications

(3 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shallow network contains rich spatial detail information, and the deep network has a strong ability to characterize semantic information. Fusing the features of deep and shallow layers can effectively improve the accuracy of the network [ 21 ]. In addition, global semantic information can provide clues to segment the category distribution, and fusing global and local features can improve the robustness of the model.…”

Section: Related Workmentioning

confidence: 99%

MFAFNet: A Lightweight and Efficient Network with Multi-Level Feature Adaptive Fusion for Real-Time Semantic Segmentation

Cheng

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Currently, real-time semantic segmentation networks are intensely demanded in resource-constrained practical applications, such as mobile devices, drones and autonomous driving systems. However, most of the current popular approaches have difficulty in obtaining sufficiently large receptive fields, and they sacrifice low-level details to improve inference speed, leading to decreased segmentation accuracy. In this paper, a lightweight and efficient multi-level feature adaptive fusion network (MFAFNet) is proposed to address this problem. Specifically, we design a separable asymmetric reinforcement non-bottleneck module, which designs a parallel structure to extract short- and long-range contextual information and use optimized convolution to increase the inference speed. In addition, we propose a feature adaptive fusion module that effectively balances feature maps with multiple resolutions to reduce the loss of spatial detail information. We evaluate our model with state-of-the-art real-time semantic segmentation methods on the Cityscapes and Camvid datasets. Without any pre-training and post-processing, our MFAFNet has only 1.27 M parameters, while achieving accuracies of 75.9% and 69.9% mean IoU with speeds of 60.1 and 82.6 FPS on the Cityscapes and Camvid test sets, respectively. The experimental results demonstrate that the proposed method achieves an excellent trade-off between inference speed, segmentation accuracy and model size.

show abstract

Section: Related Workmentioning

confidence: 99%

MFAFNet: A Lightweight and Efficient Network with Multi-Level Feature Adaptive Fusion for Real-Time Semantic Segmentation

Cheng

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the field of RATR, there are basically no relevant literature reports on the study of semantic segmentation of ISAR images, and the research at this stage is still mainly focused on ISAR target recognition. However, in the field of optical image and SAR remote sensing, research on semantic segmentation is still a popular area of study, and there is a large amount of literature related to the research of target classification and localization [ 16 ], target detection [ 17 ], semantic segmentation [ 18 , 19 ], and instance segmentation [ 20 ]. To some extent, ISAR image component recognition can be considered as a kind of ISAR image semantic segmentation research.…”

Section: Related Workmentioning

confidence: 99%

An ISAR Image Component Recognition Method Based on Semantic Segmentation and Mask Matching

Zhu,

Zhang,

et al. 2023

Sensors

View full text Add to dashboard Cite

The inverse synthetic aperture radar (ISAR) image is a kind of target feature data acquired by radar for moving targets, which can reflect the shape, structure, and motion information of the target, and has attracted a great deal of attention from the radar automatic target recognition (RATR) community. The identification of ISAR image components in radar satellite identification missions has not been carried out in related research, and the relevant segmentation methods of optical images applied to the research of semantic segmentation of ISAR images do not achieve ideal segmentation results. To address this problem, this paper proposes an ISAR image part recognition method based on semantic segmentation and mask matching. Furthermore, a reliable automatic ISAR image component labeling method is designed, and the satellite target component labeling ISAR image samples are obtained accurately and efficiently, and the satellite target component labeling ISAR image data set is obtained. On this basis, an ISAR image component recognition method based on semantic segmentation and mask matching is proposed in this paper. U-Net and Siamese Network are designed to complete the ISAR image binary semantic segmentation and binary mask matching, respectively. The component label of the ISAR image is predicted by the mask matching results. Experiments based on satellite component labeling ISAR image datasets confirm that the proposed method is feasible and effective, and it has greater comparative advantages compared to other classical semantic segmentation networks.

show abstract

“…In order to provide a comprehensive assessment of the performance of different structural models in the field of semantic segmentation for high-resolution remote sensing, we use four metrics, including mean intersection over union (MIoU) [28], mean accuracy (MAcc) [29], pixel accuracy (PAcc) [30], and inference time (ms). Where MIoU provides a more accurate measure of the segmentation accuracy of the model at the pixel level and is robust to problems such as category imbalance that may occur in the dataset.…”

Section: Evaluation Criteriamentioning

confidence: 99%

GLFFNet: A Global and Local Features Fusion Network with Biencoder for Remote Sensing Image Segmentation

Tian

Zhang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

In recent years, semantic segmentation of high-resolution remote sensing images has been gradually applied to many important scenes. However, with the rapid development of remote sensing data acquisition technology, the existing image data processing methods are facing major challenges. Especially in the accuracy of extraction and the integrity of the edges of objects, there are often problems such as small objects being assimilated by large objects. In order to solve the above problems, based on the excellent performance of Transformer, convolution and its variants, and feature pyramids in the field of deep learning image segmentation, we designed two encoders with excellent performance to extract global high-order interactive features and low-order local feature information. These encoders are then used as the backbone to construct a global and local feature fusion network with a dual encoder (GLFFNet) to effectively complete the segmentation of remote sensing images. Furthermore, a new auxiliary training module is proposed that uses the semantic attention layer to process the extracted feature maps separately, adjust the losses, and more specifically optimize each encoder of the backbone, thus optimizing the training process of the entire network. A large number of experiments show that our model achieves 87.96% mIoU on the Potsdam dataset and 80.42% mIoU on the GID dataset, and it has superior performance compared with some state-of-the-art methods on semantic segmentation tasks in the field of remote sensing.

show abstract

A Survey on Image Semantic Segmentation Using Deep Learning Techniques

Cited by 8 publications

References 68 publications

MFAFNet: A Lightweight and Efficient Network with Multi-Level Feature Adaptive Fusion for Real-Time Semantic Segmentation

MFAFNet: A Lightweight and Efficient Network with Multi-Level Feature Adaptive Fusion for Real-Time Semantic Segmentation

An ISAR Image Component Recognition Method Based on Semantic Segmentation and Mask Matching

GLFFNet: A Global and Local Features Fusion Network with Biencoder for Remote Sensing Image Segmentation

Contact Info

Product

Resources

About