The goal of semantic segmentation is to segment the input image according to semantic
information and predict the semantic category of each pixel from a given label set. With the …

The semantic image segmentation task consists of classifying each pixel of an image into an
instance, where each instance corresponds to a class. This task is a part of the concept of …

We propose an approach to domain adaptation for semantic segmentation that is both
practical and highly accurate. In contrast to previous work, we abandon the use of …

Semantic segmentation models based on convolutional neural networks have recently
displayed remarkable performance for a multitude of applications. However, these models …

Semantic segmentation is a key problem for many computer vision tasks. While approaches
based on convolutional neural networks constantly break new records on different …

We propose to harness the potential of simulation for semantic segmentation of real-world
self-driving scenes in a domain generalization fashion. The segmentation network is trained …

Unsupervised domain adaptation (DA) has gained substantial interest in semantic
segmentation. However, almost all prior arts assume concurrent access to both labeled …

Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate
models. In this paper, we present a video prediction-based methodology to scale up training …

Semantic segmentation of nighttime images plays an equally important role as that of
daytime images in autonomous driving, but the former is much more challenging due to poor …

State-of-the-art object detectors are usually trained on public datasets. They often face
substantial difficulties when applied to a different domain, where the imaging condition …