论文标题
BOMUDANET：无监督的改编，以了解非结构化驾驶环境中的视觉场景理解
BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments
论文作者
论文摘要
我们提出了一种无监督的适应方法，用于在非结构化的交通环境中的视觉场景理解。我们的方法是为非结构化的现实场景而设计的，该场景具有密集和异质的交通，包括汽车，卡车，两轮和行人。我们描述了一种基于无监督域适应（DA）的新语义分割技术，该技术可以在RGB图像或视频中识别每个区域的类或类别。我们还提出了一种用于多源DA的新型自我训练算法（ALT-INC），可提高准确性。我们的整体方法是一种基于深度学习的技术，由无监督的神经网络组成，该网络在挑战性的印度驾驶数据集上达到了87.18％的精度。我们的方法在可能不贴合或可能包括污垢，无法识别的碎屑，坑洼等的道路上效果很好。我们方法的一个关键方面是，它还可以识别模型在测试阶段遇到的模型遇到的对象。我们将我们的方法与最先进的方法进行比较，并显示5.17％-42.9％的改善。此外，我们还进行了用户研究，以定性地验证对非结构化驾驶环境的视觉场景理解的改进。
We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians. We describe a new semantic segmentation technique based on unsupervised domain adaptation (DA), that can identify the class or category of each region in RGB images or videos. We also present a novel self-training algorithm (Alt-Inc) for multi-source DA that improves the accuracy. Our overall approach is a deep learning-based technique and consists of an unsupervised neural network that achieves 87.18% accuracy on the challenging India Driving Dataset. Our method works well on roads that may not be well-marked or may include dirt, unidentifiable debris, potholes, etc. A key aspect of our approach is that it can also identify objects that are encountered by the model for the fist time during the testing phase. We compare our method against the state-of-the-art methods and show an improvement of 5.17% - 42.9%. Furthermore, we also conduct user studies that qualitatively validate the improvements in visual scene understanding of unstructured driving environments.
