LAANet: lightweight attention-guided asymmetric network for real-time semantic segmentation

X Zhang, B Du, Z Wu, T Wan - Neural Computing and Applications, 2022‏ - Springer
With the increasing demand for real-world scenarios such as robot navigation and
autonomous driving, how to achieve a good trade-off between segmentation accuracy …

Panoptic segmentation: A review

O Elharrouss, S Al-Maadeed, N Subramanian… - arxiv preprint arxiv …, 2021‏ - arxiv.org
Image segmentation for video analysis plays an essential role in different research fields
such as smart city, healthcare, computer vision and geoscience, and remote sensing …

Learning discriminative feature representation with pixel-level supervision for forest smoke recognition

H Tao, Q Duan, M Lu, Z Hu - Pattern Recognition, 2023‏ - Elsevier
Existing vision-based smoke recognition methods still face the issues of low detection rates
and high false alarm rates in complex scenes. One reason is that they label light smoke and …

[HTML][HTML] Two-step domain adaptation for underwater image enhancement

Q Jiang, Y Zhang, F Bao, X Zhao, C Zhang, P Liu - Pattern Recognition, 2022‏ - Elsevier
In recent years, underwater image enhancement methods based on deep learning have
achieved remarkable results. Since the images obtained in complex underwater scenarios …

Uavformer: A composite transformer network for urban scene segmentation of uav images

S Yi, X Liu, J Li, L Chen - Pattern Recognition, 2023‏ - Elsevier
Urban scenes segmentation based on UAV (Unmanned aerial vehicle) view is a
fundamental task for the applications of smart city such as city planning, land use monitoring …

Self-attention neural architecture search for semantic image segmentation

Z Fan, G Hu, X Sun, G Wang, J Dong, C Su - Knowledge-Based Systems, 2022‏ - Elsevier
Self-attention can capture long-distance dependencies and is widely used in semantic
segmentation. Existing methods mainly use two kinds of self-attentions, ie, spatial attention …

Thresholding-accelerated convolutional neural network for aeroengine turbine blade segmentation

J Zheng, C Tang, Y Sun - Expert Systems with Applications, 2024‏ - Elsevier
Turbine blades can only be detected nondestructively and precisely using industrial
computed tomography (CT). The accuracy of CT image segmentation, which is a key step in …

High-order paired-ASPP for deep semantic segmentation networks

X Sun, Y Zhang, C Chen, S **e, J Dong - Information Sciences, 2023‏ - Elsevier
Current semantic segmentation models only exploit first-order information, while rarely
exploring high-order semantics. However, traditional first-order statistics are insufficient to …

Hybrid feature enhancement network for few-shot semantic segmentation

H Min, Y Zhang, Y Zhao, W Jia, Y Lei, C Fan - Pattern Recognition, 2023‏ - Elsevier
Although few-shot semantic segmentation methods have been widely studied in computer
vision field, it still has room for improvement. In this work, we propose to enrich the feature …

Gaussian dynamic convolution for efficient single-image segmentation

X Sun, C Chen, X Wang, J Dong… - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging
software. Lightweight neural network is one practical and effective way to accomplish the …