论文标题
以较弱的注释学习可靠的海上障碍物检测
Learning with Weak Annotations for Robust Maritime Obstacle Detection
论文作者
论文摘要
强大的海上障碍物检测对于安全导航自动船和及时避免碰撞至关重要。当前的最新技术基于在大型数据集中训练的深度分割网络。但是，此类数据集的每个像素地面真相标记是劳动密集型且昂贵的。我们提出了一个新的脚手架学习制度（SLR），该脚手架的注释较弱，包括水边缘，地平线位置和障碍物边界框来训练基于细分的障碍检测网络，从而减少了所需的地面真相标记工作，将其减少二十个。 SLR从弱注释中训练初始模型，然后在重新估计分割伪标签和改善网络参数之间交替。实验表明，使用SLR在弱注释上训练的海上障碍分割网络不仅匹配，而且优于接受密集地面真相标签的相同网络，这是一个了不起的结果。除了提高精度外，SLR还增加了域的概括，可用于较低的手动注释负载，用于域的适应性。 SLR代码和预训练的模型可在https://github.com/lojzezust/slr上找到。
Robust maritime obstacle detection is critical for safe navigation of autonomous boats and timely collision avoidance. The current state-of-the-art is based on deep segmentation networks trained on large datasets. However, per-pixel ground truth labeling of such datasets is labor-intensive and expensive. We propose a new scaffolding learning regime (SLR) that leverages weak annotations consisting of water edges, the horizon location, and obstacle bounding boxes to train segmentation-based obstacle detection networks, thereby reducing the required ground truth labeling effort by a factor of twenty. SLR trains an initial model from weak annotations and then alternates between re-estimating the segmentation pseudo-labels and improving the network parameters. Experiments show that maritime obstacle segmentation networks trained using SLR on weak annotations not only match but outperform the same networks trained with dense ground truth labels, which is a remarkable result. In addition to the increased accuracy, SLR also increases domain generalization and can be used for domain adaptation with a low manual annotation load. The SLR code and pre-trained models are available at https://github.com/lojzezust/SLR .
