2020/07/01 by Tiange Xiang, Chaoyi Zhang, Xiang, Tiange +9 · 6 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #AI in cancer detection #Advanced Neural Network Applications #Architecture #Artificial intelligence #Cell Image Analysis Techniques #Code (set theory) #Computer Vision and Pattern Recognition (cs.CV) #Computer architecture #Computer engineering #Computer science #Deep learning #Encoder #Engineering #FOS: Computer and information sciences #FOS: Electrical engineering #Image (mathematics) #Image and Video Processing (eess.IV) #Inpainting #Machine Learning (cs.LG) #Machine learning #Net (polyhedron) #Programming language #Segmentation #Task (project management) #cs.CV #cs.LG #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2007.00243
published in ArXiv.org · 10 pages, 4 figures, MICCAI2020
openalex publication_date 2020/07/01 · arxiv created 2020/07/06 · arxiv updated 2020/07/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
U-Net has become one of the state-of-the-art deep learning-based approaches for modern computer vision tasks such as semantic segmentation, super resolution, image denoising, and inpainting. Previous extensions of U-Net have focused mainly on the modification of its existing building blocks or the development of new functional modules for performance gains. As a result, these variants usually lead to an unneglectable increase in model complexity. To tackle this issue in such U-Net variants, in this paper, we present a novel Bi-directional O-shape network (BiO-Net) that reuses the building blocks in a recurrent manner without introducing any extra parameters. Our proposed bi-directional skip connections can be directly adopted into any encoder-decoder architecture to further enhance its capabilities in various task domains. We evaluated our method on various medical image analysis tasks and the results show that our BiO-Net significantly outperforms the vanilla U-Net as well as other state-of-the-art methods. Our code is available at https://github.com/tiangexiang/BiO-Net.