29 citations · 158 across the 40 of their papers we have counts for
46 papers
Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model
Claudia Cuttano, Antonio Tavera, Fabio Cermelli +2
Many practical applications require training of semantic segmentation models on unlabelled datasets and their execution on low-resource hardware. Distillation from a trained source…
FedDrive v2: an Analysis of the Impact of Label Skewness in Federated Semantic Segmentation for Autonomous Driving
Eros Fanì, Marco Ciccone, Barbara Caputo
We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic Segmentation in Autonomous Driving. While the first version aims at studying the effect of dom…
Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation
Shyam Nandan Rai, Fabio Cermelli, Barbara Caputo +1
Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem. Ho…
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition
Gabriele Berton, Gabriele Trivigno, Barbara Caputo +1
Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features. This is typically done through image retrieval, wh…
Unmasking Anomalies in Road-Scene Segmentation
Shyam Nandan Rai, Fabio Cermelli, Dario Fontanel +2
Anomaly segmentation is a critical task for driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about ea…
EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences Prediction
Amirshayan Nasirimajd, Simone Alberto Peirone, Chiara Plizzari +1
This report presents the technical details of our approach for the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition. Our approach is based on…
Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognition
Gabriele Trivigno, Gabriele Berton, Juan Aragon +2
Visual Place recognition is commonly addressed as an image retrieval problem. However, retrieval methods are impractical to scale to large datasets, densely sampled from city-wide…
What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations
Chiara Plizzari, Toby Perrett, Barbara Caputo +1
We propose and address a new generalisation problem: can a model trained for action recognition successfully classify actions when they are performed within a previously unseen sce…
Are Local Features All You Need for Cross-Domain Visual Place Recognition?
Giovanni Barbarani, Mohamad Mostafa, Hajali Bayramov +4
Visual Place Recognition is a task that aims to predict the coordinates of an image (called query) based solely on visual clues. Most commonly, a retrieval approach is adopted, whe…
Bringing Online Egocentric Action Recognition into the wild
Gabriele Goletto, Mirco Planamente, Barbara Caputo +1
To enable a safe and effective human-robot cooperation, it is crucial to develop models for the identification of human activities. Egocentric vision seems to be a viable solution…
Hierarchical Instance Mixing across Domains in Aerial Segmentation
Edoardo Arnaudo, Antonio Tavera, Fabrizio Dominici +2
We investigate the task of unsupervised domain adaptation in aerial semantic segmentation and discover that the current state-of-the-art algorithms designed for autonomous driving…
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
Donald Shenaj, Eros Fanì, Marco Toldo +6
Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the co…
Detecting the unknown in Object Detection
Dario Fontanel, Matteo Tarantino, Fabio Cermelli +1
Object detection methods have witnessed impressive improvements in the last years thanks to the design of novel neural network architectures and the availability of large scale dat…
Learning Sequential Descriptors for Sequence-based Visual Place Recognition
Riccardo Mereu, Gabriele Trivigno, Gabriele Berton +2
In robotics, Visual Place Recognition is a continuous process that receives as input a video stream to produce a hypothesis of the robot's current position within a map of known pl…
FreeREA: Training-Free Evolution-based Architecture Search
Niccolò Cavagnero, Luca Robbiano, Barbara Caputo +1
In the last decade, most research in Machine Learning contributed to the improvement of existing models, with the aim of increasing the performance of neural networks for the solut…
Modeling Missing Annotations for Incremental Learning in Object Detection
Fabio Cermelli, Antonino Geraci, Dario Fontanel +1
Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to cat…
Augmentation Invariance and Adaptive Sampling in Semantic Segmentation of Agricultural Aerial Images
Antonio Tavera, Edoardo Arnaudo, Carlo Masone +1
In this paper, we investigate the problem of Semantic Segmentation for agricultural aerial imagery. We observe that the existing methods used for this task are designed without con…
Rethinking Visual Geo-localization for Large-Scale Applications
Gabriele Berton, Carlo Masone, Barbara Caputo
Visual Geo-localization (VG) is the task of estimating the position where a given photo was taken by comparing it with a large database of images of known locations. To investigate…
Deep Visual Geo-localization Benchmark
Gabriele Berton, Riccardo Mereu, Gabriele Trivigno +4
In this paper, we propose a new open-source benchmarking framework for Visual Geo-localization (VG) that allows to build, train, and test a wide range of commonly used architecture…
Improving Generalization in Federated Learning by Seeking Flat Minima
Debora Caldarola, Barbara Caputo, Marco Ciccone
Models trained in federated settings often suffer from degraded performances and fail at generalizing, especially when facing heterogeneous scenarios. In this work, we investigate…
FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving
Lidia Fantauzzo, Eros Fanì, Debora Caldarola +4
Semantic Segmentation is essential to make self-driving vehicles autonomous, enabling them to understand their surroundings by assigning individual pixels to known categories. Howe…
Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation
Fabio Cermelli, Massimiliano Mancini, Samuel Rota Buló +2
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are…
Learning Semantics for Visual Place Recognition through Multi-Scale Attention
Valerio Paolicelli, Antonio Tavera, Carlo Masone +2
In this paper we address the task of visual place recognition (VPR), where the goal is to retrieve the correct GPS coordinates of a given query image against a huge geotagged galle…
Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclients
Riccardo Zaccone, Andrea Rizzardi, Debora Caldarola +2
Federated Learning (FL) allows training machine learning models in privacy-constrained scenarios by enabling the cooperation of edge devices without requiring local data sharing. T…