DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection
Limited by the encoder-decoder architecture, learning-based edge detectors usually have
difficulty predicting edge maps that satisfy both correctness and crispness. With the recent …
difficulty predicting edge maps that satisfy both correctness and crispness. With the recent …
[HTML][HTML] Multi-scale pseudo labeling for unsupervised deep edge detection
Deep learning currently rules edge detection. However, the impressive progress heavily
relies on high-quality manually annotated labels which require a significant amount of labor …
relies on high-quality manually annotated labels which require a significant amount of labor …
Zero-shot edge detection with SCESAME: Spectral clustering-based ensemble for segment anything model estimation
H Yamagiwa, Y Takase, H Kambe… - Proceedings of the …, 2024 - openaccess.thecvf.com
This paper proposes a novel zero-shot edge detection with SCESAME, which stands for
Spectral Clustering-based Ensemble for Segment Anything Model Estimation, based on the …
Spectral Clustering-based Ensemble for Segment Anything Model Estimation, based on the …
MuGE: Multiple Granularity Edge Detection
Edge segmentation is well-known to be subjective due to personalized annotation styles
and preferred granularity. However most existing deterministic edge detection methods …
and preferred granularity. However most existing deterministic edge detection methods …
Bio-inspired XYW parallel pathway edge detection network
X Pang, C Lin, F Li, Y Pan - Expert Systems with Applications, 2024 - Elsevier
Edge detection is of critical importance for middle-level and high-level tasks in computer
vision. Existing edge detection methods usually use VGG16 as the encoding network and …
vision. Existing edge detection methods usually use VGG16 as the encoding network and …
RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses
Detecting edges in images suffers from the problems of (P1) heavy imbalance between
positive and negative classes as well as (P2) label uncertainty owing to disagreement …
positive and negative classes as well as (P2) label uncertainty owing to disagreement …
An Efficient Muscle Segmentation Method Via Bayesian Fusion of Probabilistic Shape Modeling and Deep Edge Detection
J Wang, G Chen, TJ Zhang, N Wu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Objective: Paraspinal muscle segmentation and reconstruction from MR images are critical
to implement quantitative assessment of chronic and recurrent low back pains. Due to …
to implement quantitative assessment of chronic and recurrent low back pains. Due to …
Boosting edge detection via Fusing Spatial and Frequency Domains
Deep learning-based edge detection methods have shown great advantages and obtained
promising performance. However, most of the current methods only extract features from the …
promising performance. However, most of the current methods only extract features from the …
Saliency and edge features-guided end-to-end network for salient object detection
C Yang, Y Xiao, L Chu, Z Yu, J Zhou… - Expert Systems with …, 2024 - Elsevier
The rapid development of the Vision Transformer backbones has enabled the capture of
feature information with global dependencies, leading to excellent performance in salient …
feature information with global dependencies, leading to excellent performance in salient …
SFMnet: Edge detection of HABs based on spatial feature mapping encoder-decoder network
GK Wu, QX Sun, BP Zhang, J Xu - Ocean Engineering, 2024 - Elsevier
Achieving high-accuracy real-time recognition of marine red tide algae images is crucial in
implementing red tide algae early warning systems. However, due to uneven lighting and …
implementing red tide algae early warning systems. However, due to uneven lighting and …