SRInpaintor: When Super-Resolution Meets Transformer for Image Inpainting

Li, Feng; Li, Anqi; Qin, Jia; Bai, Huihui; Wang, Lin; Cong, Runmin; Zhao, Yao

doi:10.1109/tci.2022.3190142

Cited by 9 publications

(3 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transformers in Medical Image Segmentation. The success of Vision Transformer (ViT) [10] in various computer vision tasks has led to its integration into medical image segmentation [41,11,38,42,22]. Some studies use transformers for image representation [14], while others propose hybrid encoders combining transformers and convolutional neural networks (CNNs) [7].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Mutual consistency learning for semi-supervised medical image segmentation

Zhang

et al. 2022

Medical Image Analysis

110

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

“…And the QaTa-COV19 dataset includes 9258 annotated COVID-19 chest radiographs. The text annotations for both datasets are derived from [22].…”

Section: Experiments Setupmentioning

confidence: 99%

Mutual consistency learning for semi-supervised medical image segmentation

Zhang

et al. 2022

Medical Image Analysis

110

View full text Add to dashboard Cite

“…Thanks to the powerful feature representation capabilities of deep learning, it has been widely used to address the computer vision task, such as enhancement [1]- [4], detection [5]- [14], super-resolution [15]- [20], and medical image processing including lung nodules segmentation [21], brain and braintumor segmentation [22], polyp segmentation [23], brain image synthesis [24], retinal image non-uniform illumination removal [25] etc. For each different task, due to the differences in imaging equipment and disease characteristics, different segmentation models need to be designed separately.…”

Section: Introductionmentioning

confidence: 99%

Boundary Guided Semantic Learning for Real-Time COVID-19 Lung Infection Segmentation System

Cong

Zhang

Yang

et al. 2022

IEEE Trans. Consumer Electron.

Self Cite

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) continues to have a negative impact on healthcare systems around the world, though the vaccines have been developed and national vaccination coverage rate is steadily increasing. At the current stage, automatically segmenting the lung infection area from CT images is essential for the diagnosis and treatment of COVID-19. Thanks to the development of deep learning technology, some deep learning solutions for lung infection segmentation have been proposed. However, due to the scattered distribution, complex background interference and blurred boundaries, the accuracy and completeness of the existing models are still unsatisfactory. To this end, we propose a boundary guided semantic learning network (BSNet) in this paper. On the one hand, the dualbranch semantic enhancement module that combines the toplevel semantic preservation and progressive semantic integration is designed to model the complementary relationship between different high-level features, thereby promoting the generation of more complete segmentation results. On the other hand, the mirror-symmetric boundary guidance module is proposed to accurately detect the boundaries of the lesion regions in a mirrorsymmetric way. Experiments on the publicly available dataset demonstrate that our BSNet outperforms the existing state-ofthe-art competitors and achieves a real-time inference speed of 44 FPS. The code and results of our BSNet can be found from the link of https://github.com/rmcong/BSNet.

show abstract