Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
This work addresses the problem of computational efficiency in semantic segmentation for applications like autonomous driving, though it appears incremental as it builds on existing cascade and pyramid methods.
The paper tackles efficient semantic segmentation by proposing a Waterfall Atrous Spatial Pooling architecture, which achieves state-of-the-art accuracy on Pascal VOC and Cityscapes datasets while reducing parameters and memory footprint.
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.