# BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture

arXiv: https://arxiv.org/abs/2007.00243 · HTML: https://mlsanity.com/paper/2007.00243/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2020.

## Built on by (most cited first, 25 of 25)

- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [Pick of the Bunch: Detecting Infrared Small Targets Beyond Hit-Miss Trade-Offs via Selective Rank-Aware Attention](https://mlsanity.com/paper/2408.03717/) (2024)
- [BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation](https://mlsanity.com/paper/2106.14033/) (2021)
- [Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions](https://mlsanity.com/paper/2304.06662/) (2023)
- [Feature Enhancer Segmentation Network (FES-Net) for Vessel Segmentation](https://mlsanity.com/paper/2309.03535/) (2023)
- [ESDMR-Net: A Lightweight Network With Expand-Squeeze and Dual Multiscale Residual Connections for Medical Image Segmentation](https://mlsanity.com/paper/2312.10585/) (2023)
- [Advancing Medical Image Segmentation with Mini-Net: A Lightweight Solution Tailored for Efficient Segmentation of Medical Images](https://mlsanity.com/paper/2405.17520/) (2024)
- [MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation](https://mlsanity.com/paper/2305.08396/) (2023)
- [LMBF-Net: A Lightweight Multipath Bidirectional Focal Attention Network for Multifeatures Segmentation](https://mlsanity.com/paper/2407.02871/) (2024)
- [U-Netmer: U-Net meets Transformer for medical image segmentation](https://mlsanity.com/paper/2304.01401/) (2023)
- [LMBiS-Net: A Lightweight Multipath Bidirectional Skip Connection based CNN for Retinal Blood Vessel Segmentation](https://mlsanity.com/paper/2309.04968/) (2023)
- [Shape-intensity knowledge distillation for robust medical image segmentation](https://mlsanity.com/paper/2409.17503/) (2024)
- [Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond](https://mlsanity.com/paper/2203.05709/) (2022)
- [SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks](https://mlsanity.com/paper/2307.02953/) (2023)
- [Inter- and intra-uncertainty based feature aggregation model for semi-supervised histopathology image segmentation](https://mlsanity.com/paper/2403.12767/) (2024)
- [MRF-UNets: Searching UNet with Markov Random Fields](https://mlsanity.com/paper/2207.06168/) (2022)
- [CM-MLP: Cascade Multi-scale MLP with Axial Context Relation Encoder for Edge Segmentation of Medical Image](https://mlsanity.com/paper/2208.10701/) (2022)
- [Head and Neck Tumor Segmentation from [18F]F-FDG PET/CT Images Based on 3D Diffusion Model](https://mlsanity.com/paper/2401.17593/) (2024)
- [RRCANet: Recurrent Reusable-Convolution Attention Network for Infrared Small Target Detection](https://mlsanity.com/paper/2506.02393/) (2025)
- [Partial Graph Reasoning for Neural Network Regularization](https://mlsanity.com/paper/2106.01805/) (2021)
- [Color Space-based HoVer-Net for Nuclei Instance Segmentation and Classification](https://mlsanity.com/paper/2203.01940/) (2022)
- [LDMRes-Net: Enabling Efficient Medical Image Segmentation on IoT and Edge Platforms](https://mlsanity.com/paper/2306.06145/) (2023)
- [PL-Net: Progressive Learning Network for Medical Image Segmentation](https://mlsanity.com/paper/2110.14484/) (2021)
- [WSC-Trans: A 3D network model for automatic multi-structural segmentation of temporal bone CT](https://mlsanity.com/paper/2211.07143/) (2022)
- [PhagoStat a scalable and interpretable end to end framework for efficient quantification of cell phagocytosis in neurodegenerative disease studies](https://mlsanity.com/paper/2304.13764/) (2023)

## Abstract (arXiv)

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.