BriefGPT.xyz
Aug, 2019
对语义分割模型鲁棒性的基准测试
Benchmarking the Robustness of Semantic Segmentation Models
HTML
PDF
Christoph Kamann, Carsten Rother
TL;DR
本研究的目的是针对 DeepLabv3+ 模型在语义分割应用中的鲁棒性进行全面调查，研究结果显示性能与鲁棒性有很大关系，而有些架构属性则对鲁棒性产生了显著影响。
Abstract
When designing a
semantic segmentation
module for a practical application, such as autonomous driving, it is crucial to understand the
robustness
of the module with respect to a wide range of
→