Deep learning has become the method of choice to tackle real-world problems in different
domains, partly because of its ability to learn from data and achieve impressive performance …

High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range
of exposures, which is important in image processing, computer graphics, and computer …

As acquiring pixel-wise annotations of real-world images for semantic segmentation is a
costly process, a model can instead be trained with more accessible synthetic data and …

Self-training is a competitive approach in domain adaptive segmentation, which trains the
network with the pseudo labels on the target domain. However inevitably, the pseudo labels …

Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source
domain (eg synthetic data) to the target domain (eg real-world data) without requiring further …

This paper focuses on the unsupervised domain adaptation of transferring the knowledge
from the source domain to the target domain in the context of semantic segmentation …

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

The divergence between labeled training data and unlabeled testing data is a significant
challenge for recent deep learning models. Unsupervised domain adaptation (UDA) …

We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised
domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D …

While self-training has advanced semi-supervised semantic segmentation, it severely suffers
from the long-tailed class distribution on real-world semantic segmentation datasets that …