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 …
autonomous driving, how to achieve a good trade-off between segmentation accuracy …
Panoptic segmentation: A review
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 …
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 …
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
In recent years, underwater image enhancement methods based on deep learning have
achieved remarkable results. Since the images obtained in complex underwater scenarios …
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 …
fundamental task for the applications of smart city such as city planning, land use monitoring …
Self-attention neural architecture search for semantic image segmentation
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 …
segmentation. Existing methods mainly use two kinds of self-attentions, ie, spatial attention …
Thresholding-accelerated convolutional neural network for aeroengine turbine blade segmentation
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 …
computed tomography (CT). The accuracy of CT image segmentation, which is a key step in …
High-order paired-ASPP for deep semantic segmentation networks
Current semantic segmentation models only exploit first-order information, while rarely
exploring high-order semantics. However, traditional first-order statistics are insufficient to …
exploring high-order semantics. However, traditional first-order statistics are insufficient to …
Hybrid feature enhancement network for few-shot semantic segmentation
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 …
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
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 …
software. Lightweight neural network is one practical and effective way to accomplish the …