Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation

EA Mansour, O Unal, S Saha, B Bejar… - arxiv preprint arxiv …, 2024 - arxiv.org
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 …

Leveraging Confident Image Regions for Source-Free Domain-Adaptive Object Detection

ML Mekhalfi, D Boscaini, F Poiesi - arxiv preprint arxiv:2501.10081, 2025 - arxiv.org
Source-free domain-adaptive object detection is an interesting but scarcely addressed topic.
It aims at adapting a source-pretrained detector to a distinct target domain without resorting …

Controlling semantics of diffusion‐augmented data for unsupervised domain adaptation

H Ridley, R Alcover‐Couso… - IET Computer …, 2025 - Wiley Online Library
Unsupervised domain adaptation (UDA) offers a compelling solution to bridge the gap
between labelled synthetic data and unlabelled real‐world data for training semantic …

[PDF][PDF] Unsupervised domain adaptation in panoptic segmentation: Unsupervised adaptive panoptic segmentation with language guidance and instance-aware …

EA Mansour - 2024 - research-collection.ethz.ch
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 …