An effective CNN and Transformer complementary network for medical image segmentation

Article Computer Science, Artificial Intelligence

Cubic-cross convolutional attention and count prior embedding for smoke segmentation

Feiniu Yuan et al.

Summary: The proposed method addresses the challenges of smoke image segmentation by introducing a count prior structure and count prior attention mechanism, which effectively capture the characteristics of smoke images. Experimental results demonstrate superior performance compared to existing methods.

PATTERN RECOGNITION (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep High-Resolution Representation Learning for Visual Recognition

Jingdong Wang et al.

Summary: The High-Resolution Network (HRNet) maintains high-resolution representations and exchanges information across resolutions, resulting in superior performance in various applications such as human pose estimation, semantic segmentation, and object detection.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Inter-Slice Context Residual Learning for 3D Medical Image Segmentation

Jianpeng Zhang et al.

Summary: In this paper, we propose the 3D context residual network (ConResNet) for accurate segmentation of 3D medical images, which incorporates context residual modules and context attention mapping to improve segmentation accuracy. Experimental results show that the proposed model outperforms other methods in brain tumor and pancreas segmentation tasks. The network architecture is well-designed and demonstrates high reliability.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A confidence prior for image dehazing

Feiniu Yuan et al.

Summary: By unifying and understanding various image dehazing priors under the same framework, we proposed a novel prior that can freely control the suppression degree of outliers by adjusting the confidence ratio, effectively removing the influence of outliers. This new prior achieved significantly better performance than existing state-of-the-art methods in experiments on both natural and synthetic images.

PATTERN RECOGNITION (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A Gated Recurrent Network With Dual Classification Assistance for Smoke Semantic Segmentation

Feiniu Yuan et al.

Summary: This study proposes a Classification-assisted Gated Recurrent Network (CGRNet) for smoke semantic segmentation, greatly improving performance at image level through dual classification assistance in smoke segmentation strategy.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

CGNet: A Light-Weight Context Guided Network for Semantic Segmentation

Tianyi Wu et al.

Summary: The research presents a lightweight and efficient semantic segmentation network CGNet, which captures contextual information in all stages of the network through context-guided technology, designed specifically to increase segmentation accuracy and reduce memory usage. Experimental results show that CGNet achieves good performance on the Cityscapes dataset.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications