2 citations · 3 across the 7 of their papers we have counts for
8 papers
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
Davide Caffagni, Alberto Compagnoni, Federico Melis +5
Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an…
Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models
Davide Caffagni, Sara Sarto, Marcella Cornia +5
Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in connecting vision and language, yet their proficiency in fundamental visual reasoning…
Lost in Translation? Vocabulary Alignment for Source-Free Adaptation in Open-Vocabulary Semantic Segmentation
Silvio Mazzucco, Carl Persson, Mattia Segu +4
We introduce VocAlign, a novel source-free domain adaptation framework specifically designed for VLMs in open-vocabulary semantic segmentation. Our method adopts a student-teacher…
Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation
Reza Qorbani, Gianluca Villani, Theodoros Panagiotakopoulos +8
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 no…
To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation
Marc Botet Colomer, Pier Luigi Dovesi, Theodoros Panagiotakopoulos +6
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…
Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions
Theodoros Panagiotakopoulos, Pier Luigi Dovesi, Linus Härenstam-Nielsen +1
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…
Real-Time Semantic Stereo Matching
Pier Luigi Dovesi, Matteo Poggi, Lorenzo Andraghetti +4
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 stru…
Enhancing self-supervised monocular depth estimation with traditional visual odometry
Lorenzo Andraghetti, Panteleimon Myriokefalitakis, Pier Luigi Dovesi +4
Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras. In this field, deep learning yielded outstandi…