Domain Generalization by Solving Jigsaw Puzzles
F.M. Carlucci, A. D’Innocente, S. Bucci, B. Caputo and T. Tommasi
CVPR 2019 (oral) [PDF - Project Page - BIBTEX]
@InProceedings{Carlucci_2019_CVPR,
author = {Carlucci, Fabio M. and D'Innocente, Antonio and Bucci, Silvia and Caputo, Barbara and Tommasi, Tatiana},
title = {Domain Generalization by Solving Jigsaw Puzzles},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}
From source to target and back: symmetric bi-directional adaptive GAN
P. Russo, F.M. Carlucci, T. Tommasi and B. Caputo
CVPR 2018 [PDF - BIBTEX]
@inproceedings{russo17sbadagan,
title={From source to target and back: symmetric bi-directional adaptive GAN},
author={Russo, Paolo and Carlucci, Fabio Maria and Tommasi, Tatiana and Caputo, Barbara},
booktitle={CVPR},
year={2018}
}
Bridging between Computer and Robot Vision through Data Augmentation: a Case Study on Object Recognition
A. D’Innocente, F.M. Carlucci, M. Colosi and B. Caputo
ICVS 2017 (Best Paper Award finalist) [PDF - Project Page - BIBTEX]
@inproceedings{d2017bridging,
title={Bridging between Computer and Robot Vision through Data Augmentation: a Case Study on Object Recognition},
author={D'Innocente, Antonio and Carlucci, Fabio Maria and Colosi, Mirco and Caputo, Barbara},
booktitle={The International Conference on Computer Vision Systems, ICVS},
year={2017}
}
AutoDIAL: Automatic DomaIn Alignment Layers
F.M. Carlucci, L. Porzi, B. Caputo, E. Ricci and S. Rota Bulò
ICCV 2017 [PDF - Project Page - BIBTEX]
@inproceedings{carlucci2017auto,
title={AutoDIAL: Automatic DomaIn Alignment Layers},
author={Carlucci, Fabio Maria and Porzi, Lorenzo and Caputo, Barbara and Ricci, Elisa and Bulo, Samuel Rota},
booktitle={International Conference on Computer Vision (ICCV)},
year={2017}
}
DE2CO: Deep Depth Colorization
F.M. Carlucci, P. Russo and B. Caputo
ICRA 2018 & RA-L [PDF - Video - BIBTEX]
@inproceedings{carlucci20172,
title={DE2CO: Deep Depth Colorization},
author={Carlucci, Fabio Maria and Russo, Paolo and Caputo, Barbara},
booktitle={ICRA 2018},
year={2018}
}
Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation
F.M. Carlucci, L. Porzi, B. Caputo, E. Ricci and S. Rota Bulò
ICIAP (oral - Best Student Paper) 2017 [PDF - BIBTEX]
@Inbook{Carlucci2017,
author="Carlucci, Fabio Maria
and Porzi, Lorenzo
and Caputo, Barbara
and Ricci, Elisa
and Bul{\`o}, Samuel Rota",
editor="Battiato, Sebastiano
and Gallo, Giovanni
and Schettini, Raimondo
and Stanco, Filippo",
title="Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation",
bookTitle="Image Analysis and Processing - ICIAP 2017 : 19th International Conference, Catania, Italy, September 11-15, 2017, Proceedings, Part I",
year="2017",
publisher="Springer International Publishing",
address="Cham",
pages="357--369",
abstract="The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains. Alleviating the domain shift problem, especially in the challenging setting where no labeled data are available for the target domain, is paramount for having visual recognition systems working in the wild. As the problem stems from a shift among distributions, intuitively one should try to align them. In the literature, this has resulted in a stream of works attempting to align the feature representations learned from the source and target domains by introducing appropriate regularization terms in the objective function. In this work we propose a different strategy and we act directly at the distribution level by introducing DomaIn Alignment Layers (DIAL) which reduce the domain shift by matching the source and target feature distributions to a canonical one. Our experimental evaluation, conducted on a widely used public benchmark, demonstrates the advantages of the proposed domain adaptation strategy.",
isbn="978-3-319-68560-1",
doi="10.1007/978-3-319-68560-1_32",
url="https://doi.org/10.1007/978-3-319-68560-1_32"
}
A deep representation for depth images from synthetic data
F.M. Carlucci, P. Russo and B. Caputo
ICRA 2017 [PDF - Project Page - BIBTEX]
@inproceedings{carlucci2016deep,
title={A deep representation for depth images from synthetic data},
author={Carlucci, Fabio Maria and Russo, Paolo and Caputo, Barbara},
booktitle={Proceedings of the IEEE International Conference on Robotics and Automation, ICRA 2017},
year={2017}
}
When Naive Bayes Nearest Neighbors Meet Convolutional Neural Networks
I. Kuzborskij, F.M. Carlucci and B. Caputo
CVPR 2016 [PDF - Project Page - BIBTEX]
@inproceedings{kuzborskij2016naive,
title={When Naive Bayes Nearest Neighbors Meet Convolutional Neural Networks},
author={Kuzborskij, Ilja and Maria Carlucci, Fabio and Caputo, Barbara},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={2100--2109},
year={2016}
}
Explicit representation of social norms for social robots
F.M. Carlucci, L. Nardi, L. Iocchi and D. Nardi
IROS 2015 [PDF - Project Page - BIBTEX]
@inproceedings{carlucci2015explicit,
title={Explicit representation of social norms for social robots},
author={Carlucci, Fabio Maria and Nardi, Lorenzo and Iocchi, Luca and Nardi, Daniele},
booktitle={Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on},
pages={4191--4196},
year={2015},
organization={IEEE}
}