Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation
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 …
autonomous driving and AR/VR applications. However, the deployment of such models has …
[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 …
autonomous driving and AR/VR applications. However, the deployment of such models has …
Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics
Developing a reliable vision system is a fundamental challenge for robotic technologies (eg,
indoor service robots and outdoor autonomous robots) which can ensure reliable navigation …
indoor service robots and outdoor autonomous robots) which can ensure reliable navigation …
C^ 2DA: Contrastive and Context-aware Domain Adaptive Semantic Segmentation
Unsupervised domain adaptive semantic segmentation (UDA-SS) aims to train a model on
the source domain data (eg, synthetic) and adapt the model to predict target domain data …
the source domain data (eg, synthetic) and adapt the model to predict target domain data …
Decision Support Systems for Adaptive Experimental Design of Autonomous, Off-Road Ground Vehicles
JM Gregory - 2024 - search.proquest.com
The rapid advancement of artificial intelligence, machine learning, human robot interaction,
and safe learning and optimization has led to significant leaps in component-and behavior …
and safe learning and optimization has led to significant leaps in component-and behavior …
Automatic segmentation using knowledge distillation with ensemble models (ASKDEM)
A Buschiazzo, M Russell, P Osteen… - Unmanned Systems …, 2024 - spiedigitallibrary.org
Fielding deep learning artificial intelligence (AI) capabilities in environments that are not well
represented within training datasets remains a challenge in deploying reliable perception …
represented within training datasets remains a challenge in deploying reliable perception …