Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
复制标题
DOI：
10.3390/s19245361
复制
发表时间：
2019-12-02
期刊：
影响因子：
3.9
通讯作者：
Savakis, Andreas
中科院分区：
文献类型：
--
作者：
Artacho, Bruno;Savakis, Andreas
提出了一种新的高效的语义分割体系结构，该体系结构基于“瀑布”Arous空间池体系结构，在减少网络参数数量和内存占用的同时，实现了较高的准确率。建议的瀑布架构利用了级联架构中渐进过滤的效率，同时保持了可与空间金字塔配置相媲美的多尺度视场。此外，我们的方法不依赖于条件随机场的后处理阶段，这进一步降低了复杂性和所需的训练时间。我们证明了带有ResNet主干的瀑布方法是一种健壮和高效的语义分割体系结构，可以获得最先进的结果，同时显著减少了Pascal VOC数据集和城市景观数据集的参数数量。
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.