Modeling Missing Annotations for Incremental Learning in Object Detection,
Fabio Cermelli, Antonino Geraci, Dario Fontanel, Barbara Caputo,
CVPR (CLVision Workshop) 2022, June, New Orleans (USA).
Bib file
/ Arxiv
/ Code
Hi, I’m Fabio and I'm a never-ending learner, especially interested in
deep learning and computer vision.
In July 20203, I obtained the Ph.D. at the VANDAL (Visual AND Multimodal Applied Learning)
laboratory at Politecnico di Torino
(Italy), in collaboration with Italian Institute of
Technology, supervised by prof. Barbara Caputo.
The main goal of my research is to enable neural networks to increase their
knowledge over time. In addition, I believe that the future of deep learning
is toward reducing human supervision. For this reason, I'm also focusing on
weakly-supervised semantic segmentation.
CV / Google Scholar / Email
Publications
Incremental Learning in Semantic Segmentation from Image Labels,
Fabio Cermelli, Dario Fontanel, Antonio Tavera, Marco Ciccone, Barbara Caputo,
CVPR 2022, June, New Orleans (USA).
Bib file
/ Arxiv
/ Code
Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation,
Antonio Tavera, Fabio Cermelli, Carlo Masone, Barbara Caputo,
Winter Conference on Applications of Computer Vision, January 2022, Hawaii (USA).
Bib file
/ Arxiv
/ Code
Prototype-based Incremental Few-Shot Segmentation,
Fabio Cermelli, Massimiliano Mancini, Yongqin Xian, Zeynep Akata, Barbara Caputo,
British Machine Vision Conference, November 22-25 2021, Virtual.
Bib file
/ Arxiv
/ Code
Detecting Anomalies in Semantic Segmentation with Prototypes,
Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Barbara Caputo,
SAIAD Workshop CVPR, June 2021, Virtual.
Bib file
A Closer Look at Self-training for Zero-Label Semantic Segmentation,
Pastore Giuseppe, Fabio Cermelli, Yongqin Xian, Massimiliano Mancini, Zeynep Akata, Barbara Caputo,
L2ID Workshop CVPR, June 2021, Virtual.
Bib file
/ Arxiv
/ Code
On the Challenges of Open World Recognition under Shifting Visual Domains,
Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Barbara Caputo,
IEEE Robotics and Automation Letters 2020, December
Bib file
Boosting Deep Open World Recognition by Clustering,
Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo,
IEEE Robotics and Automation Letters 2020, July
Bib file
/ Arxiv
Modeling the Background for Incremental Learning in Semantic Segmentation,
Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo,
CVPR 2020, June, Seattle (USA).
Bib file
/ Arxiv
/ Code
/ Website
The RGB-D Triathlon: Towards Agile Visual Toolboxes for Robots,
Fabio Cermelli, Massimiliano Mancini, Elisa Ricci, Barbara Caputo,
IROS 2019, November, Macao (Macau).
Bib file
/ Arxiv
/ Code
Discovering Latent Domains for Unsupervised Domain Adaptation Through Consistency,
Massimiliano Mancini, Lorenzo Porzi, Fabio Cermelli, Barbara Caputo,
ICIAP 2019, September, Trento (Italy).
Bib file