论文标题
多域语义分割与金字塔融合
Multi-domain semantic segmentation with pyramidal fusion
论文作者
论文摘要
我们提出了在ECCV 2020举行的强大视觉挑战的语义细分竞赛中的提交。该竞赛要求将相同的模型从三个不同领域提交七个基准。我们的方法是基于带有锥体融合的SwiftNet架构。我们通过单级193维软效果输出来解决不一致的分类法。我们努力用大批量训练，以稳定对硬识别问题的优化，并倾向于对批处理统计的平稳演变。我们通过在纪录 - 企业损失中实施自定义的向后步骤，并在冷冻人口统计之前使用小型农作物来实现这一目标。我们的模型在RVC语义细分挑战以及Wilddash 2排行榜上排名第一。这表明，金字塔融合不仅为有效的轻巧骨干，而且在用于多域应用的大规模设置中都具有竞争力。
We present our submission to the semantic segmentation contest of the Robust Vision Challenge held at ECCV 2020. The contest requires submitting the same model to seven benchmarks from three different domains. Our approach is based on the SwiftNet architecture with pyramidal fusion. We address inconsistent taxonomies with a single-level 193-dimensional softmax output. We strive to train with large batches in order to stabilize optimization of a hard recognition problem, and to favour smooth evolution of batchnorm statistics. We achieve this by implementing a custom backward step through log-sum-prob loss, and by using small crops before freezing the population statistics. Our model ranks first on the RVC semantic segmentation challenge as well as on the WildDash 2 leaderboard. This suggests that pyramidal fusion is competitive not only for efficient inference with lightweight backbones, but also in large-scale setups for multi-domain application.
