Convolutional Networks (ConvNets) excel at semantic segmentation and have become a vital component for perception in autonomous driving. Enabling an all-encompassing view of street-scenes, omnidirectional cameras present themselves as a perfect fit in such systems. Most segmentation models for parsing urban environments operate on common, narrow Field of View (FoV) images. Transferring these models from the domain they were designed for to 360-degree perception, their performance drops dramatically, e.g., by an absolute 30.0% (mIoU) on established test-beds. To bridge the gap in terms of FoV and structural distribution between the imaging domains, we introduce Efficient Concurrent Attention Networks (ECANets), directly capturing the inherent long-range dependencies in omnidirectional imagery. In addition to the learned attention-based contextual priors that can stretch across 360-degree images, we upgrade model training by leveraging multi-source and omni-supervised learning, taking advantage of both: Densely labeled and unlabeled data originating from multiple datasets. To foster progress in panoramic image segmentation, we put forward and extensively evaluate models on Wild PAnoramic Semantic Segmentation (WildPASS), a dataset designed to capture diverse scenes from all around the globe. Our novel model, training regimen and multi-source prediction fusion elevate the performance (mIoU) to new state-of-the-art results on the public PASS (60.2%) and the fresh WildPASS (69.0%) benchmarks.
翻译: Convolution Nets (Convillal Nets) 擅长语义分割, 并已成为自主驱动感知的至关重要组成部分。 使得对街道- 摄像头和成像领域之间结构分布的全方位观点能够包罗万象的全方位观察, 全方位摄像头显示在这样的系统中。 大部分城市环境分解模型的模型在普通的、 狭窄的视野( FoV) 图像上运行。 将这些模型从设计用于360度感知的域迁移到360度感知, 其性能显著下降, 例如, 在已建立的测试台上以绝对的 30. 0% (MIOU) 为绝对值下降。 为了缩小FOV和成像领域之间结构分布上的差距, 我们引入了高效的同步关注网络(ECANets), 直接捕捉全方位图像中固有的长期依赖性能模型。 除了学习到超过360度图像, 我们通过多源和全方位监督的学习来提升模型培训模式, 提升模型培训模式培训,, 利用以下两种方法: 高层次的、 我们的上标和未标的公众级的图像- 上的数据- 上的数据- 高级的图像- Servial- sal- stradeal- sal- sal- laveal- sal- sal- sal- sal- sal- laction- sal- salation- laction- sal- salation- sal- sal- salation- salvicalation- salation- salction- salation- salction- salation- salation- salation- salation- sal- sal- sal- salation- sal- sal- sal- sal- salation- sal- sal- salation- salation- salction- salation- salation- salation- sal- sal- sal- sal- sal- salation- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal