Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation

TL;DR

This paper introduces a novel Waterfall Atrous Spatial Pooling architecture for semantic segmentation that improves accuracy, reduces parameters, and eliminates the need for postprocessing, demonstrating state-of-the-art results on Pascal VOC and Cityscapes datasets.

Contribution

The paper presents a new Waterfall architecture that enhances multiscale feature extraction efficiently without relying on postprocessing, outperforming existing methods.

Findings

Achieves state-of-the-art accuracy on Pascal VOC and Cityscapes datasets.

Reduces network parameters and memory footprint significantly.

Eliminates the need for postprocessing with Conditional Random Fields.

Abstract

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.