Papers › Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation

Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation

6 Dec 2019arXiv:1912.03183archive 2025-07-28

Bruno Artacho, Andreas Savakis

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.

PaperPDFCode

Code

bmartacho/WASP officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation Cityscapes test WASPnet (ours) Mean IoU (class) 70.5% #81 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes val WASPnet (ours) mIoU 74% #78 of 99 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test WASPnet-CRF (ours) Mean IoU 79.6% #32 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 val WASPnet-CRF (ours) mIoU 80.41% #11 of 29 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections