LASNet: A Light-Weight Asymmetric Spatial Feature Network for Real-Time Semantic Segmentation

Chen, Yu; Zhan, Weida; Jiang, Yichun; Zhu, Daming; Guo, Ruifeng; Xu, Xiaoyu

doi:10.3390/electronics11193238

Cited by 4 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it can be difficult to simultaneously achieve real-time performance and high accuracy due to the computational complexity of semantic segmentation models. Some popular methods "ENet" [46], "ICNet [214]", "LASNet" [215], "SFANet" [44], "ShelfNet" [216] and "BiSeNet" [217] have applied semantic segmentation methods in real time. For example, ShelfNet and BiSeNet have achieved comparable segmentation accuracy to state-of-the-art off-line models with a four to five times faster inference speed.…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

Deep-Learning-Based Approaches for Semantic Segmentation of Natural Scene Images: A Review

et al. 2023

View full text Add to dashboard Cite

The task of semantic segmentation holds a fundamental position in the field of computer vision. Assigning a semantic label to each pixel in an image is a challenging task. In recent times, significant advancements have been achieved in the field of semantic segmentation through the application of Convolutional Neural Networks (CNN) techniques based on deep learning. This paper presents a comprehensive and structured analysis of approximately 150 methods of semantic segmentation based on CNN within the last decade. Moreover, it examines 15 well-known datasets in the semantic segmentation field. These datasets consist of 2D and 3D image and video frames, including general, indoor, outdoor, and street scenes. Furthermore, this paper mentions several recent techniques, such as SAM, UDA, and common post-processing algorithms, such as CRF and MRF. Additionally, this paper analyzes the performance evaluation of reviewed state-of-the-art methods, pioneering methods, common backbone networks, and popular datasets. These have been compared according to the results of Mean Intersection over Union (MIoU), the most popular evaluation metric of semantic segmentation. Finally, it discusses the main challenges and possible solutions and underlines some future research directions in the semantic segmentation task. We hope that our survey article will be useful to provide a foreknowledge to the readers who will work in this field.

show abstract

Section: Discussion and Future Directionsmentioning

confidence: 99%

Deep-Learning-Based Approaches for Semantic Segmentation of Natural Scene Images: A Review

et al. 2023

View full text Add to dashboard Cite

show abstract

A Visual-Semantic Interactive Carcass Spine Interface Segmentation Method

Zhang,

Cai

2022

2022 International Conference on Intelligent Manufacturing and Industrial Big Data (ICIMIBD)

View full text Add to dashboard Cite

Real-Time Semantic Segmentation Algorithm for Street Scenes Based on Attention Mechanism and Feature Fusion

Wu,

Xiong,

Wang

2024

Electronics

View full text Add to dashboard Cite

In computer vision, the task of semantic segmentation is crucial for applications such as autonomous driving and intelligent surveillance. However, achieving a balance between real-time performance and segmentation accuracy remains a significant challenge. Although Fast-SCNN is favored for its efficiency and low computational complexity, it still faces difficulties when handling complex street scene images. To address this issue, this paper presents an improved Fast-SCNN, aiming to enhance the accuracy and efficiency of semantic segmentation by incorporating a novel attention mechanism and an enhanced feature extraction module. Firstly, the integrated SimAM (Simple, Parameter-Free Attention Module) increases the network’s sensitivity to critical regions of the image and effectively adjusts the feature space weights across channels. Additionally, the refined pyramid pooling module in the global feature extraction module captures a broader range of contextual information through refined pooling levels. During the feature fusion stage, the introduction of an enhanced DAB (Depthwise Asymmetric Bottleneck) block and SE (Squeeze-and-Excitation) attention optimizes the network’s ability to process multi-scale information. Furthermore, the classifier module is extended by incorporating deeper convolutions and more complex convolutional structures, leading to a further improvement in model performance. These enhancements significantly improve the model’s ability to capture details and overall segmentation performance. Experimental results demonstrate that the proposed method excels in processing complex street scene images, achieving a mean Intersection over Union (mIoU) of 71.7% and 69.4% on the Cityscapes and CamVid datasets, respectively, while maintaining inference speeds of 81.4 fps and 113.6 fps. These results indicate that the proposed model effectively improves segmentation quality in complex street scenes while ensuring real-time processing capabilities.

show abstract

LASNet: A Light-Weight Asymmetric Spatial Feature Network for Real-Time Semantic Segmentation

Cited by 4 publications

References 51 publications

Deep-Learning-Based Approaches for Semantic Segmentation of Natural Scene Images: A Review

Deep-Learning-Based Approaches for Semantic Segmentation of Natural Scene Images: A Review

A Visual-Semantic Interactive Carcass Spine Interface Segmentation Method

Real-Time Semantic Segmentation Algorithm for Street Scenes Based on Attention Mechanism and Feature Fusion

Contact Info

Product

Resources

About