… Furthermore, few works have been done to propagate uncertainties in object detectors and
semantic segmentation networks to other modules, such as tracking and motion planning. …

… In this paper, we present the first principled approach for benchmarking real-time
segmentation networks. The decoupled design of the framework separates encoder and decoder …

… self-driving cars. We propose a novel deep network architecture for image segmentation that
… On the Cityscapes dataset, the new network achieves higher segmentation accuracy than …

… However, we argue that the SS for autonomous driving system is quite different from the …
networks such as FCN, SegNet and ENet, we will show that our loss is able to drive the networks …

… However, we argue that the SS associated with autonomous driving system [3] is quite …
that our loss is able to attract the network’s attention to important objects during self-driving. …

… Consistent with a common concern of deep neural networks, semantic segmentation models
trained on publicly labeled datasets, such as [4], [9], [10] do not usually adapt well to new …

… segmentation is a critical component for street understanding task in autonomous driving
field… To this end, we present a Boundary Aware Network (BASeg) for semantic segmentation by …

… Thus, several minor adjustments are sufficient to convert a classification neural network
into a semantic segmentation neural network. It is implemented on AlexNet and VGG-16 …

… chose semantic segmentation as … segmentation An RGB image is a high-dimensional source
of data, with pixels being the smallest units of semantic information. Semantic segmentation …

… framework for low illumination scenes, which includes a light enhancement network and a
segmentation network. 3) The experimental results of Dark Zurich-test and Nighttime driving-…