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

TL;DR

BiO-Net introduces recurrent bi-directional skip connections into encoder-decoder architectures, enhancing performance in medical image analysis tasks without increasing model complexity.

Contribution

The paper proposes a novel BiO-Net with recurrent bi-directional skip connections that reuses existing blocks without adding parameters, improving U-Net variants.

Findings

BiO-Net outperforms vanilla U-Net in medical image analysis tasks.

BiO-Net achieves significant performance gains over state-of-the-art methods.

The approach does not increase model complexity.

Abstract

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.