Adaptation of semantic segmentation networks to different visual conditions is vital for robust perception in autonomous cars and robots. However, previous work has shown that most …
Unsupervised cross-domain scene segmentation approach adapts the source model to the target domain, which utilizes two-stage strategies to minimize the inter-domain and intra …
The increasing relevance of panoptic segmentation is tied to the advancements in autonomous driving and AR/VR applications. However, the deployment of such models has …
Z Liang, C Li - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Due to unaffordable computational costs, the regularized disparity in iterative stereo matching is typically maintained at a lower resolution than the input. To regress the full …
Z Wang, Y Zhang, Z Zhang, Z Jiang, Y Yu, L Li… - Remote Sensing, 2023 - mdpi.com
Semantic segmentation based on optical images can provide comprehensive scene information for intelligent vehicle systems, thus aiding in scene perception and decision …
Z Xie, R Qiu, S Wang, X Tan, Y Xie, L Ma - arXiv preprint arXiv:2406.10531, 2024 - arxiv.org
Night-time scene parsing aims to extract pixel-level semantic information in night images, aiding downstream tasks in understanding scene object distribution. Due to limited labeled …
Unsupervised domain adaptation (UDA) is an important solution for the cross-domain problem in semantic segmentation. Existing segmentation UDA methods mainly consider …
In unsupervised domain adaptation (UDA), where models are trained on source data (eg, synthetic) and adapted to target data (eg, real-world) without target annotations, addressing …
The increasing relevance of panoptic segmentation is tied to the advancements in autonomous driving and AR/VR applications. However, the deployment of such models has …