As UDA methods for semantic segmentation are usually GPU memory intensive, most previous methods operate only on downscaled images. We question this design as low-resolution predictions often fail to preserve fine details. The alternative of training with random crops of high-resolution images ...
"ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation "解读 MoveOn 电子信息1 人赞同了该文章 研究背景和意义 图1 现有多目标域自适应方法 大多数以往多目标域泛化算法都是采用单目标域模型风格化迁移不同目标域数据来构建多目标域模型。 这些方法取得了良好的效果,但其性能...
Papers - Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation shanzsz 逐渐变捞的研究生6 人赞同了该文章 前言 由于训练数据数据分布与实际应用场景的数据分布在大部分情况下都是不一样的,因此就会带来模型精度的下降,而域自适应目的就是解决这一问题。为解决这一问题,作者打算采用...
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation Lukas Hoyer ETH Zurich lhoyer@vision.ee.ethz.ch Dengxin Dai MPI for Informatics ddai@mpi-inf.mpg.de Luc Van Gool ETH Zurich & KU Leuven vangool@v...
Unsupervised domain adaptation (UDA) in semantic segmentation is a fundamental yet promising task relieving the need for laborious annotation works. However, the domain shifts/discrepancies problem in this task compromise the final segmentation performance. Based on our observation, the main causes of th...
2 Dec 2022·Yinghong Liao,Wending Zhou,Xu Yan,Shuguang Cui,Yizhou Yu,Zhen Li· Measuring and alleviating the discrepancies between the synthetic (source) and real scene (target) data is the core issue for domain adaptive semantic segmentation. Though recent works have introduced depth information ...
{Junjue Wang and Zhuo Zheng and Ailong Ma and Xiaoyan Lu and Yanfei Zhong}, title={Love{DA}: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation}, month=oct, year=2021, publisher={Zenodo}, doi={10.5281/zenodo.5706578}, url={https://doi.org/10.5281/zenodo....
The more detailed domain-adaptive semantic segmentation of HRDA, compared to the previous state-of-the-art UDA method DAFormer, can also be observed in example predictions from the Cityscapes validation set. HRDA.Slider.Demo.mp4 HRDA can be further extended to domain generalization lifting the re...
1. Introduction Semantic segmentation, aiming at assigning the seman- tic label to each pixel in an image, is a fundamental prob- lem in computer vision. Driven by the availability of large-scale datasets and the advancements in deep neural net...
Li Y, Yuan L, Vasconcelos N (2019) Bidirectional learning for domain adaptation of semantic segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 6936–6945 Bateson M, Kervadec H, Dolz J, Lombaert H, Ayed IB (2022) Source-free domain ad...