Search Results for author: Angelo Porrello

Found 21 papers, 12 papers with code

Semantic Residual Prompts for Continual Learning

no code implementations11 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).

Continual Learning

Self-Labeling the Job Shop Scheduling Problem

1 code implementation22 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.

Job Shop Scheduling Pseudo Label +3

DistFormer: Enhancing Local and Global Features for Monocular Per-Object Distance Estimation

no code implementations6 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.

Autonomous Driving Object

TrackFlow: Multi-Object Tracking with Normalizing Flows

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.

Multi-Object Tracking Object

Input Perturbation Reduces Exposure Bias in Diffusion Models

1 code implementation27 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.

Denoising Image Generation +1

On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning

1 code implementation12 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.

Continual Learning

Spotting Virus from Satellites: Modeling the Circulation of West Nile Virus Through Graph Neural Networks

no code implementations7 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.

Graph Attention

Consistency-based Self-supervised Learning for Temporal Anomaly Localization

1 code implementation10 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.

Anomaly Detection In Surveillance Videos Self-Supervised Learning +3

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

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).

Knowledge Distillation Trajectory Forecasting +1

Continual Semi-Supervised Learning through Contrastive Interpolation Consistency

1 code implementation14 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.

Continual Learning Metric Learning

Rethinking Experience Replay: a Bag of Tricks for Continual Learning

2 code implementations12 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.

Continual Learning

The color out of space: learning self-supervised representations for Earth Observation imagery

1 code implementation22 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.

Colorization Disease Prediction +4

Dark Experience for General Continual Learning: a Strong, Simple Baseline

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.

Class Incremental Learning Knowledge Distillation

Classifying Signals on Irregular Domains via Convolutional Cluster Pooling

no code implementations13 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.

Clustering General Classification

Multi-views Embedding for Cattle Re-identification

no code implementations13 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.

Latent Space Autoregression for Novelty Detection

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.

Anomaly Detection Novelty Detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.