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 .
翻译:对自主船只的安全航行和及时避免碰撞而言,探测强力海上障碍至关重要。目前的先进技术是以在大型数据集方面受过训练的深度隔离网络为基础的。然而,这种数据集的每像素地面真实性标签是劳动密集型和昂贵的。我们提议一个新的脚架学习制度(SLR),利用由水边缘、地平线位置和障碍捆绑箱组成的薄弱注释来训练以分割为基础的障碍探测网络,从而将所需的地面真实性标签工作减少二十倍。SLR从薄弱的注释中培训一个初步模型,然后在重新估计分离假标签和改善网络参数之间进行替代。实验表明,使用微弱说明进行训练的海上障碍隔离网络不仅匹配,而且优于经过密集地面真实性标签训练的同一网络,这是一个了不起的结果。除了提高准确性外,SLRR还提高了域的全域化,并且可以用低手动的笔记号负荷来进行域适应。SLRR代码和预先训练的模型可在 https://girub.Szuze./comze上查到。