Transformer-based visual segmentation: A survey
Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …
segments or groups. This technique has numerous real-world applications, such as …
VP-Net: Voxels as points for 3-D object detection
The 3-D object detection with light detection and ranging (LiDAR) point clouds is a
challenging problem, which requires 3-D scene understanding, yet this task is critical to …
challenging problem, which requires 3-D scene understanding, yet this task is critical to …
CenterFormer: a novel cluster center enhanced transformer for unconstrained dental plaque segmentation
Dental plaque segmentation is crucial for maintaining oral health. However, accurately
segmenting dental plaque in unconstrained environments can be challenging due to its low …
segmenting dental plaque in unconstrained environments can be challenging due to its low …
Sdpt: Semantic-aware dimension-pooling transformer for image segmentation
Image segmentation plays a critical role in autonomous driving by providing vehicles with a
detailed and accurate understanding of their surroundings. Transformers have recently …
detailed and accurate understanding of their surroundings. Transformers have recently …
SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
Recent real-time semantic segmentation methods usually adopt an additional semantic
branch to pursue rich long-range context. However, the additional branch incurs undesirable …
branch to pursue rich long-range context. However, the additional branch incurs undesirable …
[HTML][HTML] Real-time semantic segmentation for autonomous driving: A review of CNNs, Transformers, and Beyond
Real-time semantic segmentation is a crucial component of autonomous driving systems,
where accurate and efficient scene interpretation is essential to ensure both safety and …
where accurate and efficient scene interpretation is essential to ensure both safety and …
An Efficient RGB-D Indoor Scene-Parsing Solution via Lightweight Multiflow Intersection and Knowledge Distillation
The rapid progression of convolutional neural networks (CNNs) has significantly improved
indoor scene parsing, transforming the fields of robotics, autonomous navigation …
indoor scene parsing, transforming the fields of robotics, autonomous navigation …
Boundary-aware spatial and frequency dual-domain transformer for remote sensing urban images segmentation
Semantic segmentation of remote sensing (RS) images refers to labeling each pixel with a
class to identify objects or land cover types. Existing mainstream spatial-domain semantic …
class to identify objects or land cover types. Existing mainstream spatial-domain semantic …
UPFormer: U-sharped perception lightweight transformer for segmentation of field grape leaf diseases
X Zhang, F Li, H Zheng, W Mu - Expert Systems with Applications, 2024 - Elsevier
In the smart agriculture community, segmentation models are de-facto for the timely
detection and identification of plant diseases. However, the complex background and the …
detection and identification of plant diseases. However, the complex background and the …
Dual-resolution transformer combined with multi-layer separable convolution fusion network for real-time semantic segmentation
K Hu, Z Xie, Q Hu - Computers & Graphics, 2024 - Elsevier
Environmental perception is crucial for unmanned mobile platforms such as autonomous
vehicles and robots. Precise and fast semantic segmentation of the surrounding scene is a …
vehicles and robots. Precise and fast semantic segmentation of the surrounding scene is a …