127 citations · 420 across the 42 of their papers we have counts for
52 papers
Is Multiple Object Tracking a Matter of Specialization?
Gianluca Mancusi, Mattia Bernardi, Aniello Panariello +3
End-to-end transformer-based trackers have achieved remarkable performance on most human-related datasets. However, training these trackers in heterogeneous scenarios poses signifi…
Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning
Matteo Mosconi, Andriy Sorokin, Aniello Panariello +6
The use of skeletal data allows deep learning models to perform action recognition efficiently and effectively. Herein, we believe that exploring this problem within the context of…
Federated Class-Incremental Learning with Hierarchical Generative Prototypes
Riccardo Salami, Pietro Buzzega, Matteo Mosconi +2
Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of tha…
Trajectory Forecasting through Low-Rank Adaptation of Discrete Latent Codes
Riccardo Benaglia, Angelo Porrello, Pietro Buzzega +2
Trajectory forecasting is crucial for video surveillance analytics, as it enables the anticipation of future movements for a set of agents, e.g. basketball players engaged in intri…
Monocular Per-Object Distance Estimation with Masked Object Modeling
Aniello Panariello, Gianluca Mancusi, Fedy Haj Ali +3
Per-object distance estimation is critical in surveillance and autonomous driving, where safety is crucial. While existing methods rely on geometric or deep supervised features, on…
TrackFlow: Multi-Object Tracking with Normalizing Flows
Gianluca Mancusi, Aniello Panariello, Angelo Porrello +3
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 compl…
On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning
Lorenzo Bonicelli, Matteo Boschini, Emanuele Frascaroli +6
Humans can learn incrementally, whereas neural networks forget previously acquired information catastrophically. Continual Learning (CL) approaches seek to bridge this gap by facil…
Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
Emanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra +3
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…
Input Perturbation Reduces Exposure Bias in Diffusion Models
Mang Ning, Enver Sangineto, Angelo Porrello +2
Denoising Diffusion Probabilistic Models have shown an impressive generation quality, although their long sampling chain leads to high computational costs. In this paper, we observ…
Latent Spectral Regularization for Continual Learning
Emanuele Frascaroli, Riccardo Benaglia, Matteo Boschini +4
While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget catastrophically whenever they face a changing train…
On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning
Lorenzo Bonicelli, Matteo Boschini, Angelo Porrello +2
Rehearsal approaches enjoy immense popularity with Continual Learning (CL) practitioners. These methods collect samples from previously encountered data distributions in a small me…
Spotting Virus from Satellites: Modeling the Circulation of West Nile Virus Through Graph Neural Networks
Lorenzo Bonicelli, Angelo Porrello, Stefano Vincenzi +4
The occurrence of West Nile Virus (WNV) represents one of the most common mosquito-borne zoonosis viral infections. Its circulation is usually associated with climatic and environm…
Consistency-based Self-supervised Learning for Temporal Anomaly Localization
Aniello Panariello, Angelo Porrello, Simone Calderara +1
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 d…
Transfer without Forgetting
Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello +5
This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread application of network pretrainin…
Learning the Quality of Machine Permutations in Job Shop Scheduling
Andrea Corsini, Simone Calderara, Mauro Dell'Amico
In recent years, the power demonstrated by Machine Learning (ML) has increasingly attracted the interest of the optimization community that is starting to leverage ML for enhancing…
Effects of Auxiliary Knowledge on Continual Learning
Giovanni Bellitto, Matteo Pennisi, Simone Palazzo +4
In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information…
Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction
Luigi Filippo Chiara, Pasquale Coscia, Sourav Das +3
Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires k…
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting
Alessio Monti, Angelo Porrello, Simone Calderara +3
Accurate prediction of future human positions is an essential task for modern video-surveillance systems. Current state-of-the-art models usually rely on a "history" of past tracke…
Class-Incremental Continual Learning into the eXtended DER-verse
Matteo Boschini, Lorenzo Bonicelli, Pietro Buzzega +2
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, th…
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Matteo Fabbri, Guillem Braso, Gianluca Maugeri +6
Deep learning-based methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance. However, data acquisition in crowded pub…
Continual Semi-Supervised Learning through Contrastive Interpolation Consistency
Matteo Boschini, Pietro Buzzega, Lorenzo Bonicelli +2
Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming exa…
Avalanche: an End-to-End Library for Continual Learning
Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu +25
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing…
RMS-Net: Regression and Masking for Soccer Event Spotting
Matteo Tomei, Lorenzo Baraldi, Simone Calderara +2
The recently proposed action spotting task consists in finding the exact timestamp in which an event occurs. This task fits particularly well for soccer videos, where events corres…
Generalising via Meta-Examples for Continual Learning in the Wild
Alessia Bertugli, Stefano Vincenzi, Simone Calderara +1
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. As a step towards this…