← Search

Pier Luigi Dovesi

4 accepted papers

2025

Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation

CVPR 2025poster

Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. However, large shifts between training and test domains degrade their performance, requiring fine-tuning f…

2023

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

ICCV 2023poster

The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events. However, the high computational costs associated with brute-force adaptation make this paradigm unfeasible for real-world applications. I…

Cited by 13PDFcodeScholar
2022

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

ECCV 2022poster

"Unsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data and is, in most cases, carried out in offline manner. However, domain changes may occur continuously and unpredictably during deployment (e.g. sudden weather changes). In such conditions, deep neu…

2020

Real-Time Semantic Stereo Matching

ICRA 2020poster

Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields. To fully accomplish this task, an autonomous agent has to infer the 3D structure of the sensed scene (to know where it looks at) and its content (to know what it sees). To tackle the two tasks, d…

Cited by 84SourceScholar