Search Results for author: Antonio Tavera

Found 9 papers, 8 papers with code

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning

1 code implementation5 Oct 2022 Donald Shenaj, Eros Fanì, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli, Marco Ciccone, Pietro Zanuttigh, Barbara Caputo

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 collected data.

Augmentation Invariance and Adaptive Sampling in Semantic Segmentation of Agricultural Aerial Images

1 code implementation17 Apr 2022 Antonio Tavera, Edoardo Arnaudo, Carlo Masone, Barbara Caputo

We observe that the existing methods used for this task are designed without considering two characteristics of the aerial data: (i) the top-down perspective implies that the model cannot rely on a fixed semantic structure of the scene, because the same scene may be experienced with different rotations of the sensor; (ii) there can be a strong imbalance in the distribution of semantic classes because the relevant objects of the scene may appear at extremely different scales (e. g., a field of crops and a small vehicle).

Semantic Segmentation

FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving

1 code implementation28 Feb 2022 Lidia Fantauzzo, Eros Fani', Debora Caldarola, Antonio Tavera, Fabio Cermelli, Marco Ciccone, Barbara Caputo

For similar reasons, Federated Learning has been recently introduced as a new machine learning paradigm aiming to learn a global model while preserving privacy and leveraging data on millions of remote devices.

Autonomous Driving Domain Generalization +3

Learning Semantics for Visual Place Recognition through Multi-Scale Attention

1 code implementation24 Jan 2022 Valerio Paolicelli, Antonio Tavera, Carlo Masone, Gabriele Berton, Barbara Caputo

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 gallery.

Visual Place Recognition

A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images

1 code implementation7 Dec 2021 Edoardo Arnaudo, Fabio Cermelli, Antonio Tavera, Claudio Rossi, Barbara Caputo

Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets.

Incremental Learning Knowledge Distillation +3

Incremental Learning in Semantic Segmentation from Image Labels

1 code implementation CVPR 2022 Fabio Cermelli, Dario Fontanel, Antonio Tavera, Marco Ciccone, Barbara Caputo

As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally.

Incremental Learning Semantic Segmentation

Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation

1 code implementation22 Oct 2021 Antonio Tavera, Fabio Cermelli, Carlo Masone, Barbara Caputo

The pixel-wise adversarial training is assisted by a novel sample selection procedure, that handles the imbalance between source and target data, and a knowledge distillation strategy, that avoids overfitting towards the few target images.

Autonomous Driving Cross-Domain Few-Shot +3

Reimagine BiSeNet for Real-Time Domain Adaptation in Semantic Segmentation

1 code implementation22 Oct 2021 Antonio Tavera, Carlo Masone, Barbara Caputo

To the best of our knowledge, we are the first to present a real-time adversarial approach for assessing the domain adaption problem in semantic segmentation.

Domain Adaptation Real-Time Semantic Segmentation

IDDA: a large-scale multi-domain dataset for autonomous driving

no code implementations17 Apr 2020 Emanuele Alberti, Antonio Tavera, Carlo Masone, Barbara Caputo

To support work in this direction, this paper contributes a new large scale, synthetic dataset for semantic segmentation with more than 100 different source visual domains.

Autonomous Driving Domain Adaptation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.