# Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation

arXiv: https://arxiv.org/abs/1912.03183 · HTML: https://mlsanity.com/paper/1912.03183/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2019.

## Built on by (most cited first, 5 of 5)

- [A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation](https://mlsanity.com/paper/2112.09747/) (2021)
- [OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation](https://mlsanity.com/paper/2103.10180/) (2021)
- [Trans2Unet: Neural fusion for Nuclei Semantic Segmentation](https://mlsanity.com/paper/2407.17181/) (2024)
- [BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations](https://mlsanity.com/paper/2112.10716/) (2021)
- [Semantic Segmentation for Urban-Scene Images](https://mlsanity.com/paper/2110.13813/) (2021)

## Abstract (arXiv)

We propose a new efficient architecture for semantic segmentation, based on a "Waterfall" Atrous Spatial Pooling architecture, that achieves a considerable accuracy increase while decreasing the number of network parameters and memory footprint. The proposed Waterfall architecture leverages the efficiency of progressive filtering in the cascade architecture while maintaining multiscale fields-of-view comparable to spatial pyramid configurations. Additionally, our method does not rely on a postprocessing stage with Conditional Random Fields, which further reduces complexity and required training time. We demonstrate that the Waterfall approach with a ResNet backbone is a robust and efficient architecture for semantic segmentation obtaining state-of-the-art results with significant reduction in the number of parameters for the Pascal VOC dataset and the Cityscapes dataset.