no code implementations • 25 May 2024 • Angelo Porrello, Lorenzo Bonicelli, Pietro Buzzega, Monica Millunzi, Simone Calderara, Rita Cucchiara
The fine-tuning of deep pre-trained models has recently revealed compositional properties.
no code implementations • 29 Mar 2024 • Giovanni Bellitto, Federica Proietto Salanitri, Matteo Pennisi, Matteo Boschini, Angelo Porrello, Simone Calderara, Simone Palazzo, Concetto Spampinato
We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting.
no code implementations • 11 Mar 2024 • Martin Menabue, Emanuele Frascaroli, Matteo Boschini, Enver Sangineto, Lorenzo Bonicelli, Angelo Porrello, Simone Calderara
Most of these methods organize these vectors in a pool of key-value pairs, and use the input image as query to retrieve the prompts (values).
1 code implementation • 22 Jan 2024 • Andrea Corsini, Angelo Porrello, Simone Calderara, Mauro Dell'Amico
Inspired by Semi- and Self-Supervised learning, we show that it is possible to easily train generative models by sampling multiple solutions and using the best one according to the problem objective as a pseudo-label.
no code implementations • 6 Jan 2024 • Aniello Panariello, Gianluca Mancusi, Fedy Haj Ali, Angelo Porrello, Simone Calderara, Rita Cucchiara
Existing approaches rely on two scales: local information (i. e., the bounding box proportions) or global information, which encodes the semantics of the scene as well as the spatial relations with neighboring objects.
no code implementations • ICCV 2023 • Gianluca Mancusi, Aniello Panariello, Angelo Porrello, Matteo Fabbri, Simone Calderara, Rita Cucchiara
The field of multi-object tracking has recently seen a renewed interest in the good old schema of tracking-by-detection, as its simplicity and strong priors spare it from the complex design and painful babysitting of tracking-by-attention approaches.
no code implementations • 5 May 2023 • Lorenzo Bonicelli, Matteo Boschini, Emanuele Frascaroli, Angelo Porrello, Matteo Pennisi, Giovanni Bellitto, Simone Palazzo, Concetto Spampinato, Simone Calderara
Humans can learn incrementally, whereas neural networks forget previously acquired information catastrophically.
1 code implementation • 2 Feb 2023 • Emanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra, Simone Calderara, Andrea Passerini, Stefano Teso
We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and compute predictions by reasoning consistently with prior knowledge.
1 code implementation • 27 Jan 2023 • Mang Ning, Enver Sangineto, Angelo Porrello, Simone Calderara, Rita Cucchiara
Denoising Diffusion Probabilistic Models have shown an impressive generation quality, although their long sampling chain leads to high computational costs.
Ranked #1 on Image Generation on FFHQ 128 x 128
1 code implementation • 9 Jan 2023 • Emanuele Frascaroli, Riccardo Benaglia, Matteo Boschini, Luca Moschella, Cosimo Fiorini, Emanuele Rodolà, Simone Calderara
While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget catastrophically whenever they face a changing training data distribution.
1 code implementation • 12 Oct 2022 • Lorenzo Bonicelli, Matteo Boschini, Angelo Porrello, Concetto Spampinato, Simone Calderara
By means of extensive experiments, we show that applying LiDER delivers a stable performance gain to several state-of-the-art rehearsal CL methods across multiple datasets, both in the presence and absence of pre-training.
no code implementations • 7 Sep 2022 • Lorenzo Bonicelli, Angelo Porrello, Stefano Vincenzi, Carla Ippoliti, Federica Iapaolo, Annamaria Conte, Simone Calderara
In this paper, we seek to predict WNV circulation by feeding Deep Neural Networks (DNNs) with satellite images, which have been extensively shown to hold environmental and climatic features.
1 code implementation • 10 Aug 2022 • Aniello Panariello, Angelo Porrello, Simone Calderara, Rita Cucchiara
This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training.
Ranked #12 on Anomaly Detection In Surveillance Videos on XD-Violence
Anomaly Detection In Surveillance Videos Self-Supervised Learning +3
no code implementations • 7 Jul 2022 • Andrea Corsini, Simone Calderara, Mauro Dell'Amico
Finally, we empirically demonstrate the value of predicting the quality of machine permutations by enhancing the performance of a simple Tabu Search algorithm inspired by the works in the literature.
1 code implementation • 3 Jun 2022 • Giovanni Bellitto, Matteo Pennisi, Simone Palazzo, Lorenzo Bonicelli, Matteo Boschini, Simone Calderara, Concetto Spampinato
In this paper we propose a new, simple, CL algorithm that focuses on solving the current task in a way that might facilitate the learning of the next ones.
1 code implementation • 1 Jun 2022 • Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello, Giovanni Bellitto, Matteo Pennisi, Simone Palazzo, Concetto Spampinato, Simone Calderara
This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL).
no code implementations • ICIAP 2022 • Mang Ning, Xiaoliang Ma, Yao Lu, Simone Calderara, Rita Cucchiara
In this paper, we introduce SeeFar to achieve vehicle speed estimation and traffic flow analysis based on YOLOv5 and DeepSORT from a moving drone.
1 code implementation • 25 Apr 2022 • Luigi Filippo Chiara, Pasquale Coscia, Sourav Das, Simone Calderara, Rita Cucchiara, Lamberto Ballan
Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications.
no code implementations • CVPR 2022 • Alessio Monti, Angelo Porrello, Simone Calderara, Pasquale Coscia, Lamberto Ballan, Rita Cucchiara
To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones).
1 code implementation • 3 Jan 2022 • Matteo Boschini, Lorenzo Bonicelli, Pietro Buzzega, Angelo Porrello, Simone Calderara
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion.
1 code implementation • ICCV 2021 • Matteo Fabbri, Guillem Braso, Gianluca Maugeri, Orcun Cetintas, Riccardo Gasparini, Aljosa Osep, Simone Calderara, Laura Leal-Taixe, Rita Cucchiara
Deep learning-based methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance.
1 code implementation • 14 Aug 2021 • Matteo Boschini, Pietro Buzzega, Lorenzo Bonicelli, Angelo Porrello, Simone Calderara
This work explores Continual Semi-Supervised Learning (CSSL): here, only a small fraction of labeled input examples are shown to the learner.
4 code implementations • 1 Apr 2021 • Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, Tyler L. Hayes, Matthias De Lange, Marc Masana, Jary Pomponi, Gido van de Ven, Martin Mundt, Qi She, Keiland Cooper, Jeremy Forest, Eden Belouadah, Simone Calderara, German I. Parisi, Fabio Cuzzolin, Andreas Tolias, Simone Scardapane, Luca Antiga, Subutai Amhad, Adrian Popescu, Christopher Kanan, Joost Van de Weijer, Tinne Tuytelaars, Davide Bacciu, Davide Maltoni
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning.
no code implementations • 15 Feb 2021 • Matteo Tomei, Lorenzo Baraldi, Simone Calderara, Simone Bronzin, Rita Cucchiara
The recently proposed action spotting task consists in finding the exact timestamp in which an event occurs.
Ranked #1 on Action Spotting on SoccerNet
1 code implementation • 28 Jan 2021 • Alessia Bertugli, Stefano Vincenzi, Simone Calderara, Andrea Passerini
Future deep learning systems call for techniques that can deal with the evolving nature of temporal data and scarcity of annotations when new problems occur.
2 code implementations • 12 Oct 2020 • Pietro Buzzega, Matteo Boschini, Angelo Porrello, Simone Calderara
In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time.
1 code implementation • 17 Sep 2020 • Alessia Bertugli, Stefano Vincenzi, Simone Calderara, Andrea Passerini
In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream.
no code implementations • 20 Jul 2020 • Matteo Fabbri, Fabio Lanzi, Riccardo Gasparini, Simone Calderara, Lorenzo Baraldi, Rita Cucchiara
In this document, we report our proposal for modeling the risk of possible contagiousity in a given area monitored by RGB cameras where people freely move and interact.
1 code implementation • ECCV 2020 • Angelo Porrello, Luca Bergamini, Simone Calderara
To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion.
Ranked #2 on Vehicle Re-Identification on VeRi
1 code implementation • 1 Jul 2020 • Alessandro Simoni, Luca Bergamini, Andrea Palazzi, Simone Calderara, Rita Cucchiara
In this work we propose a deep learning pipeline to predict the visual future appearance of an urban scene.
1 code implementation • 22 Jun 2020 • Stefano Vincenzi, Angelo Porrello, Pietro Buzzega, Marco Cipriano, Pietro Fronte, Roberto Cuccu, Carla Ippoliti, Annamaria Conte, Simone Calderara
We conduct experiments on land cover classification (BigEarthNet) and West Nile Virus detection, showing that colorization is a solid pretext task for training a feature extractor.
1 code implementation • 26 May 2020 • Alessio Monti, Alessia Bertugli, Simone Calderara, Rita Cucchiara
Understanding human motion behaviour is a critical task for several possible applications like self-driving cars or social robots, and in general for all those settings where an autonomous agent has to navigate inside a human-centric environment.
Ranked #1 on Trajectory Prediction on STATS SportVu NBA [ATK]
Human motion prediction Multi-future Trajectory Prediction +3
1 code implementation • 17 May 2020 • Alessia Bertugli, Simone Calderara, Pasquale Coscia, Lamberto Ballan, Rita Cucchiara
Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications.
3 code implementations • NeurIPS 2020 • Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, Simone Calderara
Continual Learning has inspired a plethora of approaches and evaluation settings; however, the majority of them overlooks the properties of a practical scenario, where the data stream cannot be shaped as a sequence of tasks and offline training is not viable.
Ranked #12 on Continual Learning on ASC (19 tasks)
1 code implementation • CVPR 2020 • Matteo Fabbri, Fabio Lanzi, Simone Calderara, Stefano Alletto, Rita Cucchiara
At the core of the proposed method lies our Volumetric Heatmap Autoencoder, a fully-convolutional network tasked with the compression of ground-truth heatmaps into a dense intermediate representation.
Ranked #6 on 3D Human Pose Estimation on Panoptic (using extra training data)
1 code implementation • CVPR 2020 • Davide Abati, Jakub Tomczak, Tijmen Blankevoort, Simone Calderara, Rita Cucchiara, Babak Ehteshami Bejnordi
Therefore, we additionally introduce a task classifier that predicts the task label of each example, to deal with settings in which a task oracle is not available.
Ranked #3 on Continual Learning on ImageNet-50 (5 tasks)
1 code implementation • 9 Dec 2019 • Matteo Tomei, Lorenzo Baraldi, Simone Calderara, Simone Bronzin, Rita Cucchiara
Action Detection is a complex task that aims to detect and classify human actions in video clips.
no code implementations • 22 Nov 2019 • Stefano Vincenzi, Angelo Porrello, Pietro Buzzega, Annamaria Conte, Carla Ippoliti, Luca Candeloro, Alessio Di Lorenzo, Andrea Capobianco Dondona, Simone Calderara
Nowadays, Vector-Borne Diseases (VBDs) raise a severe threat for public health, accounting for a considerable amount of human illnesses.
1 code implementation • 24 Jul 2019 • Andrea Palazzi, Luca Bergamini, Simone Calderara, Rita Cucchiara
An Image Completion Network (ICN) is then trained to generate a realistic image starting from this geometric guidance.
1 code implementation • 5 Mar 2019 • Matteo Stefanini, Riccardo Lancellotti, Lorenzo Baraldi, Simone Calderara
The experiments compare our proposal with state-of-the-art solutions available in literature, demonstrating that our proposal achieve better performance.
no code implementations • 13 Feb 2019 • Angelo Porrello, Davide Abati, Simone Calderara, Rita Cucchiara
We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset.
no code implementations • 13 Feb 2019 • Luca Bergamini, Angelo Porrello, Andrea Capobianco Dondona, Ercole Del Negro, Mauro Mattioli, Nicola D'Alterio, Simone Calderara
People re-identification task has seen enormous improvements in the latest years, mainly due to the development of better image features extraction from deep Convolutional Neural Networks (CNN) and the availability of large datasets.
no code implementations • 23 Jan 2019 • Matteo Fabbri, Guido Borghi, Fabio Lanzi, Roberto Vezzani, Simone Calderara, Rita Cucchiara
Can faces acquired by low-cost depth sensors be useful to catch some characteristic details of the face?
1 code implementation • 23 Jan 2019 • Federico Fulgeri, Matteo Fabbri, Stefano Alletto, Simone Calderara, Rita Cucchiara
When you see a person in a crowd, occluded by other persons, you miss visual information that can be used to recognize, re-identify or simply classify him or her.
1 code implementation • CVPR 2019 • Davide Abati, Angelo Porrello, Simone Calderara, Rita Cucchiara
Novelty detection is commonly referred to as the discrimination of observations that do not conform to a learned model of regularity.
2 code implementations • ECCV 2018 • Matteo Fabbri, Fabio Lanzi, Simone Calderara, Andrea Palazzi, Roberto Vezzani, Rita Cucchiara
Multi-People Tracking in an open-world setting requires a special effort in precise detection.
no code implementations • 12 Dec 2017 • Guido Borghi, Matteo Fabbri, Roberto Vezzani, Simone Calderara, Rita Cucchiara
Therefore, we propose a complete framework for the estimation of the head and shoulder pose based on depth images only.
no code implementations • 7 Jul 2017 • Matteo Fabbri, Simone Calderara, Rita Cucchiara
In this paper we propose a deep architecture for detecting people attributes (e. g. gender, race, clothing ...) in surveillance contexts.
3 code implementations • 26 Jun 2017 • Andrea Palazzi, Guido Borghi, Davide Abati, Simone Calderara, Rita Cucchiara
Awareness of the road scene is an essential component for both autonomous vehicles and Advances Driver Assistance Systems and is gaining importance both for the academia and car companies.
no code implementations • 1 Jun 2017 • Stefano Alletto, Davide Abati, Simone Calderara, Rita Cucchiara, Luca Rigazio
We address unsupervised optical flow estimation for ego-centric motion.
1 code implementation • 10 May 2017 • Andrea Palazzi, Davide Abati, Simone Calderara, Francesco Solera, Rita Cucchiara
In this work we aim to predict the driver's focus of attention.
1 code implementation • 24 Nov 2016 • Andrea Palazzi, Francesco Solera, Simone Calderara, Stefano Alletto, Rita Cucchiara
Despite the advent of autonomous cars, it's likely - at least in the near future - that human attention will still maintain a central role as a guarantee in terms of legal responsibility during the driving task.
no code implementations • ICCV 2015 • Francesco Solera, Simone Calderara, Rita Cucchiara
Online Multiple Target Tracking (MTT) is often addressed within the tracking-by-detection paradigm.
no code implementations • 5 Aug 2015 • Francesco Solera, Simone Calderara, Rita Cucchiara
Modern crowd theories agree that collective behavior is the result of the underlying interactions among small groups of individuals.