Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation

TL;DR

This paper introduces Stacked U-Nets (SUNets), a simple yet effective architecture that combines multi-resolution features for natural image segmentation, achieving high performance with fewer parameters.

Contribution

The paper proposes SUNets, a novel deep network architecture that iteratively combines features across resolutions while maintaining high resolution, improving segmentation performance efficiently.

Findings

SUNets outperform traditional models on semantic segmentation benchmarks.

SUNets achieve high accuracy with fewer parameters.

The architecture effectively balances global information and high-resolution details.

Abstract

Many imaging tasks require global information about all pixels in an image. Conventional bottom-up classification networks globalize information by decreasing resolution; features are pooled and downsampled into a single output. But for semantic segmentation and object detection tasks, a network must provide higher-resolution pixel-level outputs. To globalize information while preserving resolution, many researchers propose the inclusion of sophisticated auxiliary blocks, but these come at the cost of a considerable increase in network size and computational cost. This paper proposes stacked u-nets (SUNets), which iteratively combine features from different resolution scales while maintaining resolution. SUNets leverage the information globalization power of u-nets in a deeper network architectures that is capable of handling the complexity of natural images. SUNets perform extremely well on semantic segmentation tasks using a small number of parameters.