论文标题
在语义细分中检测和检索分布式对象
Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation
论文作者
论文摘要
当在自动驾驶汽车中部署深度学习技术时，深层神经网络会不断暴露于领域的变化。其中包括，例如，天气状况，一天中的时间和长期时间变化的变化。在这项工作中，我们利用了一个深层神经网络，该网络在包含城市街景的CityScapes数据集中训练，并从其他数据集A2D2数据集中推断图像，还包含乡村和高速公路图像。我们提出了一条新型的语义类别管道，该管道通过深神经网络的预测来检测分布（OOD）段（OOD）段，并在图像斑块上的特征提取和降低后进行图像检索。在我们的实验中，我们证明了部署的OOD方法适合检测分布概念。此外，我们通过半兼容的A2D2地面真相来定性地评估图像斑块的检索，并进行定量评估，并获得高达52.2％的地图值。
When deploying deep learning technology in self-driving cars, deep neural networks are constantly exposed to domain shifts. These include, e.g., changes in weather conditions, time of day, and long-term temporal shift. In this work we utilize a deep neural network trained on the Cityscapes dataset containing urban street scenes and infer images from a different dataset, the A2D2 dataset, containing also countryside and highway images. We present a novel pipeline for semantic segmenation that detects out-of-distribution (OOD) segments by means of the deep neural network's prediction and performs image retrieval after feature extraction and dimensionality reduction on image patches. In our experiments we demonstrate that the deployed OOD approach is suitable for detecting out-of-distribution concepts. Furthermore, we evaluate the image patch retrieval qualitatively as well as quantitatively by means of the semi-compatible A2D2 ground truth and obtain mAP values of up to 52.2%.
