Massimiliano Mancini
Collaborating Faculty
Github Website massimiliano.mancini at uni-tuebingen.de Google Scholar

Profile

Massimiliano Mancini is a postdoc researcher at the Explainable Machine Learning group, led by Prof. Zeynep Akata. He completed his Ph.D. in Engineering in Computer Science at the Sapienza University of Rome, advised by Prof. Barbara Caputo and Prof. Elisa Ricci. During the Ph.D. he has been a member of the ELLIS Ph.D. program, advised by Prof. Zeynep Akata. He received his master's degree in Artificial Intelligence and Robotics with honors from the Sapienza University of Rome in 2016 and his bachelor's degree in Computer Science and Electronic Engineering from the University of Perugia in 2014. During his Ph.D. he has been a member of the Technologies of Vision lab at Fondazione Bruno Kessler and of the Visual Learning and Multimodal Applications Laboratory of the Italian Institute of Technology. During summer 2018, he was a visiting Ph.D. student in the Robotics, Perception, and Learning Laboratory at KTH Royal Institute of Technology in Stockholm.

Research

Massimiliano Mancini's research interest is mainly in breaking the closed-world assumption of pretrained models, whose knowledge is inherently limited to the particular training set they are trained on. In particular, his focus is mostly in scenarios where the input distribution is changing at test time (such as domain adaptation/generalization) and/or the new semantic concepts are added over time (such as incremental/multi-domain learning, open-world recognition, and zero-shot learning).

Publications

2022

  • "Relational Proxies: Emergent Relationships as Fine-Grained Discriminators", Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata, and Anjan Dutta, Neural Information Processing Systems (NeurIPS) 2022
  • "Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval", Abhra Chaudhuri, Massimiliano Mancini, Yanbei Chen, Zeynep Akata, and Anjan Dutta, British Machine Vision Conference (BMVC) 2022
  • "Abstracting Sketches through Simple Primitives", Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos and Zeynep Akata, European Conference on Computer Vision (ECCV) 2022
  • "BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks", Uddeshya Upadhyay, Shyamgopal Karthik, Yanbei Chen, Massimiliano Mancini, and Zeynep Akata, European Conference on Computer Vision (ECCV) 2022
  • "Semi-Supervised and Unsupervised Deep Visual Learning: A Survey", Yanbei Chen, Massimiliano Mancini, Xiatian Zhu, and Zeynep Akata, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022
  • "Attention Consistency on Visual Corruptions for Single-Source Domain Generalization", Ilke Cugu, Massimiliano Mancini, Yanbei Chen, and Zeynep Akata, CVPR Workshop on Learning With Limited Labelled Data for Image and Video 2022
  • "Learning Graph Embeddings for Open World Compositional Zero-Shot Learning", Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian, and Zeynep Akata, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022
  • "KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning", Shyamgopal Karthik, Massimiliano Mancini, and Zeynep Akata, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022

2021

  • "Revisiting Visual Product for Compositional Zero-Shot Learning", Shyamgopal Karthik, Massimiliano Mancini, and Zeynep Akata, NeurIPS Workshop on Distribution Shifts 2021
  • "Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation", Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, and Barbara Caputo, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021
  • "Prototype-based Incremental Few-Shot Semantic Segmentation", Fabio Cermelli, Massimiliano Mancini, Yongqin Xian, Zeynep Akata, and Barbara Caputo, British Machine Vision Conference (BMVC) 2021
  • "Concurrent Discrimination and Alignment for Self-Supervised Feature Learning", Anjan Dutta, Massimiliano Mancini, and Zeynep Akata, ICCV Workshop on Multi-Task Learning in Computer Vision 2021
  • "Detecting Anomalies in Semantic Segmentation with Prototypes", Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, and Barbara Caputo, CVPR Workshop on Safe and Artificial Intelligence for Automated Driving 2021
  • "A Closer Look at Self-training for Zero-Label Semantic Segmentation", Giuseppe Pastore, Fabio Cermelli, Yongqin Xian, Massimiliano Mancini, Zeynep Akata, and Barbara Caputo, CVPR Workshop on Learning from Limited and Imperfect Data 2021
  • "Cluster-driven Graph Federated Learning over Multiple Domains", Debora Caldarola, Massimiliano Mancini, Fabio Galasso, Marco Ciccone, Emanuele Rodolà, and Barbara Caputo, CVPR Workshop on Learning from Limited and Imperfect Data 2021
  • "Open World Compositional Zero-Shot Learning", Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian and Zeynep Akata, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021
  • "On the Challenges of Open World Recognition under Shifting Visual Domains", Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, and Barbara Caputo, IEEE Robotics and Automation Letters (IEEE RA-L) 2021

2020

  • "Shape Consistent 2D Keypoint Estimation under Domain Shift", Levi O. Vasconcelos, Massimiliano Mancini, Davide Boscaini, Samuel Rota Bulò, Barbara Caputo, and Elisa Ricci, IEEE International Conference on Pattern Recognition (ICPR) 2020
  • "Towards Recognizing Unseen Categories in Unseen Domains", Massimiliano Mancini, Zeynep Akata, Elisa Ricci, and Barbara Caputo, European Conference on Computer Vision (ECCV) 2020
  • "Boosting Deep Open World Recognition by Clustering", Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, and Barbara Caputo, IEEE Robotics and Automation Letters (IEEE RA-L) 2020
  • "Boosting binary masks for multi-domain learning through affine transformations", Massimiliano Mancini, Elisa Ricci, Barbara Caputo, and Samuel Rota Bulò, Machine Vision and Applications (MVA) 2020
  • "Modeling the Background for Incremental Learning in Semantic Segmentation", Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, and Barbara Caputo, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020

2019

  • "The RGB-D Triathlon: Towards Agile Visual Toolboxes for Robots", Fabio Cermelli, Massimiliano Mancini, Elisa Ricci, and Barbara Caputo, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2019
  • "Structured Domain Adaptation for 3D Keypoint Estimation", Levi O. Vasconcelos, Massimiliano Mancini, Davide Boscaini, Barbara Caputo, and Elisa Ricci, International Conference on 3D Vision (3DV) 2019 (Oral Presentation)
  • "Discovering Latent Domains for Unsupervised Domain Adaptation Through Consistency", Massimiliano Mancini, Fabio Cermelli, Lorenzo Porzi, and Barbara Caputo, International Conference on Image Analysis and Processing (ICIAP) 2019
  • "Inferring Latent Domains for Unsupervised Deep Domain Adaptation", Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulò, Elisa Ricci, and Barbara Caputo, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2019
  • "AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs", Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, and Elisa Ricci, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 (Oral Presentation)
  • "Knowledge is Never Enough: Towards Web Aided Deep Open World Recognition", Massimiliano Mancini, Hakan Karaoguz, Elisa Ricci, Patric Jensfelt and Barbara Caputo, IEEE International Conference on Robotics and Automation (ICRA) 2019

2018

  • "Adding New Tasks to a Single Network with Weight Transformations using Binary Masks", Massimiliano Mancini, Elisa Ricci, Barbara Caputo, and Samuel Rota Bulò, ECCV Task-CV Workshop 2018 (Best Paper Award Honorable Mention)
  • "Kitting in the Wild through Online Domain Adaptation", Massimiliano Mancini, Hakan Karaoguz, Elisa Ricci, Patric Jensfelt, and Barbara Caputo, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2018
  • "Best sources forward: domain generalization through source-specific nets", Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, and Elisa Ricci, IEEE International Conference on Image Processing (ICIP) 2018
  • "Boosting Domain Adaptation by Discovering Latent Domains", Massimiliano Mancini, Lorenzo Porzi Samuel Rota Bulò, Barbara Caputo, and Elisa Ricci, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 (Spotlight Presentation)
  • "Robust Place Categorization With Deep Domain Generalization", Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, and Elisa Ricci, IEEE Robotics and Automation Letters (IEEE RA-L) 2018

2017

  • "Learning Deep NBNN Representations for Robust Place Categorization", Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, and Barbara Caputo, IEEE Robotics and Automation Letters (IEEE RA-L) 2017
  • "Embedding Words and Senses Together via Joint Knowledge-Enhanced Training", Massimiliano Mancini, Jose Camacho-Collados, Ignacio Iacobacci, and Roberto Navigli, Conference on Computational Natural Language Learning (CoNLL) 2017