AIConfPaper
← Search

SIMONE CALDERARA

28 accepted papers

2026

Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature

Angelo Porrello, Pietro Buzzega, Felix Dangel, Thomas Sommariva, Riccardo Salami, Lorenzo Bonicelli +1
ICLR 2026poster

Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation drift and degraded performance. Representation drift regularization provides a natural remedy to disentangle task vectors;…

Cited by 0Source ↗Scholar ↗
2026

Distilling Linearized Behavior into Non-linear Fine-Tuning for Effective Task Arithmetic

Thomas Sommariva, Francesca Morandi, Simone Calderara, Angelo Porrello
ICML 2026poster

Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging via addition and task removal via subtraction. Fine-tuning in the tangent space of a pre-trained model (*linearized fine-tuning*) has proven particularly effective in this setting, as i…

Cited by 0Source ↗Scholar ↗
2026

Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models

Filippo Rinaldi, Aniello Panariello, Giacomo Salici, Fengyuan Liu, Marco Ciccone, Angelo Porrello +1
ICLR 2026poster

When a new release of a foundation model is published, practitioners typically need to repeat fine-tuning, even if the same task was already tackled in the previous version. A promising alternative is to reuse the parameter changes (i.e., task vectors) that capture how a model adapts to a specific t…

Cited by 0Source ↗code ↗Scholar ↗
2026

Transporting Task Vectors across Different Architectures without Training

Filippo Rinaldi, Aniello Panariello, Giacomo Salici, Angelo Porrello, Simone Calderara
ICML 2026poster

Adapting large pre-trained models to downstream tasks often produces task-specific parameter updates that are expensive to relearn for every model variant. While recent work has shown that such updates can be transferred between models with identical architectures, transferring them across models of…

Cited by 0Source ↗Scholar ↗
2025

A Second-Order Perspective on Model Compositionality and Incremental Learning

Angelo Porrello, Lorenzo Bonicelli, Pietro Buzzega, Monica Millunzi, Simone Calderara, Rita Cucchiara
ICLR 2025spotlight

The fine-tuning of deep pre-trained models has revealed compositional properties, with multiple specialized modules that can be arbitrarily composed into a single, multi-task model. However, identifying the conditions that promote compositionality remains an open issue, with recent efforts concentra…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2025

Accurate and Efficient Low-Rank Model Merging in Core Space

Aniello Panariello, Daniel Marczak, Simone Magistri, Angelo Porrello, Bartłomiej Twardowski, Andrew D. Bagdanov +2
NeurIPS 2025poster

In this paper, we address the challenges associated with merging low-rank adaptations of large neural networks. With the rise of parameter-efficient adaptation techniques, such as Low-Rank Adaptation (LoRA), model fine-tuning has become more accessible. While fine-tuning models with LoRA is highly e…

Cited by 0Source ↗code ↗Scholar ↗
2025

Closed-Form Merging of Parameter-Efficient Modules for Federated Continual Learning

Riccardo Salami, Pietro Buzzega, Matteo Mosconi, Jacopo Bonato, Luigi Sabetta, Simone Calderara
ICLR 2025poster

Model merging has emerged as a crucial technique in Deep Learning, enabling the integration of multiple models into a unified system while preserving performance and scalability. In this respect, the compositional properties of low-rank adaptation techniques (e.g., LoRA) have proven beneficial, as s…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2025

DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection

Chiara Cappellino, Gianluca Mancusi, Matteo Mosconi, Angelo Porrello, Simone Calderara, Rita Cucchiara
NeurIPS 2025poster

Open-Vocabulary object detectors can generalize to an unrestricted set of categories through simple textual prompting. However, adapting these models to rare classes or reinforcing their abilities on multiple specialized domains remains essential. While recent methods rely on monolithic adaptation s…

Cited by 0Source ↗Scholar ↗
2025

Update Your Transformer to the Latest Release: Re-Basin of Task Vectors

Filippo Rinaldi, Giacomo Capitani, Lorenzo Bonicelli, Donato Crisostomi, Federico Bolelli, ELISA FICARRA +3
ICML 2025poster

Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g., on larger and more curated datasets), the fine-tuned model becomes obsolete, losing its utility and requiring retraining…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Is Multiple Object Tracking a Matter of Specialization?

Gianluca Mancusi, Mattia Bernardi, Aniello Panariello, Angelo Porrello, Rita Cucchiara, Simone Calderara
NeurIPS 2024poster

End-to-end transformer-based trackers have achieved remarkable performance on most human-related datasets. However, training these trackers in heterogeneous scenarios poses significant challenges, including negative interference - where the model learns conflicting scene-specific parameters - and li…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Saliency-driven Experience Replay for Continual Learning

Giovanni Bellitto, Federica Proietto Salanitri, Matteo Pennisi, Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello +3
NeurIPS 2024spotlight

We present Saliency-driven Experience Replay - SER - a biologically-plausible approach based on replicating human visual saliency to enhance classification models in continual learning settings. Inspired by neurophysiological evidence that the primary visual cortex does not contribute to object mani…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

Self-Labeling the Job Shop Scheduling Problem

Andrea Corsini, Angelo Porrello, Simone Calderara, Mauro Dell'Amico
NeurIPS 2024poster

This work proposes a self-supervised training strategy designed for combinatorial problems. An obstacle in applying supervised paradigms to such problems is the need for costly target solutions often produced with exact solvers. Inspired by semi- and self-supervised learning, we show that generative…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2024

Semantic Residual Prompts for Continual Learning

Martin Menabue*, Emanuele Frascaroli, Matteo Boschini, Enver Sangineto, Lorenzo Bonicelli, Angelo Porrello* +1
ECCV 2024poster

"Prompt-tuning methods for Continual Learning (CL) freeze a large pre-trained model and train a few parameter vectors termed prompts. 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). However, as keys are lear…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2023

Input Perturbation Reduces Exposure Bias in Diffusion Models

Mang Ning, Enver Sangineto, Angelo Porrello, Simone Calderara, Rita Cucchiara
ICML 2023poster

Denoising Diffusion Probabilistic Models have shown an impressive generation quality although their long sampling chain leads to high computational costs. In this paper, we observe that a long sampling chain also leads to an error accumulation phenomenon, which is similar to the exposure bias proble…

Cited by 61Source ↗PDF ↗code ↗Scholar ↗
2023

Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal

Emanuele Marconato, Gianpaolo Bontempo, ELISA FICARRA, Simone Calderara, Andrea Passerini, Stefano Teso
ICML 2023poster

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. Our key observation is that neuro-symbolic tasks, a…

Cited by 25Source ↗PDF ↗code ↗Scholar ↗
2023

TrackFlow: Multi-Object tracking with Normalizing Flows

Gianluca Mancusi, Aniello Panariello, Angelo Porrello, Matteo Fabbri, Simone Calderara, Rita Cucchiara
ICCV 2023poster

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. In view of this, we aim at extending tracking-by-…

Cited by 16PDF ↗Scholar ↗
2022

How Many Observations Are Enough? Knowledge Distillation for Trajectory Forecasting

Alessio Monti, Angelo Porrello, Simone Calderara, Pasquale Coscia, Lamberto Ballan, Rita Cucchiara
CVPR 2022poster

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 tracked locations (e.g., 3 to 5 seconds) to predict a plausible sequence of future locations (e.g., up to the next 5 seconds).…

Cited by 78PDF ↗Scholar ↗
2022

On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning

Lorenzo Bonicelli, Matteo Boschini, Angelo Porrello, Concetto Spampinato, Simone Calderara
NeurIPS 2022accept

Rehearsal approaches enjoy immense popularity with Continual Learning (CL) practitioners. These methods collect samples from previously encountered data distributions in a small memory buffer; subsequently, they repeatedly optimize on the latter to prevent catastrophic forgetting. This work draws at…

Cited by 55Source ↗PDF ↗code ↗Scholar ↗
2022

Transfer without Forgetting

Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello, Giovanni Bellitto, Matteo Pennisi, Simone Palazzo +2
ECCV 2022poster

"This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread application of network pretraining, highlighting that it is itself subject to catastrophic forgetting. Unfortunately, this issue leads to the under-expl…

Cited by 57Source ↗PDF ↗code ↗Scholar ↗
2021

MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?

Matteo Fabbri, Guillem Brasó, Gianluca Maugeri, Orcun Cetintas, Riccardo Gasparini, Aljoša Ošep +3
ICCV 2021poster

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 public environments raises data privacy concerns -- we are not allowed to simply record and store data without the explicit…

Cited by 159PDF ↗Scholar ↗
2020

Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation

Matteo Fabbri, Fabio Lanzi, Simone Calderara, Stefano Alletto, Rita Cucchiara
CVPR 2020poster

In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective compression method to drastically reduce the size of this represent…

Cited by 123PDF ↗code ↗Scholar ↗
2020

Conditional Channel Gated Networks for Task-Aware Continual Learning

Davide Abati, Jakub Tomczak, Tijmen Blankevoort, Simone Calderara, Rita Cucchiara, Babak Ehteshami Bejnordi
CVPR 2020oral

Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this work, we introduce a novel framework to tackle this problem…

Cited by 270PDF ↗Scholar ↗
2020

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

Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, SIMONE CALDERARA
NeurIPS 2020poster

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. We work towards General Continual Learni…

Cited by 1149Source ↗PDF ↗code ↗Scholar ↗
2020

Robust Re-Identification by Multiple Views Knowledge Distillation

Angelo Porrello, Luca Bergamini, Simone Calderara
ECCV 2020poster

To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion. However, these solutions face a large drop in performance for single image queries (e.g., Image-To-Video setting). Recent works address this severe degradation by transferring temp…

Cited by 94Source ↗PDF ↗code ↗Scholar ↗
2019

Classifying Signals on Irregular Domains via Convolutional Cluster Pooling

Angelo Porrello, Davide Abati, Simone Calderara, Rita Cucchiara
AISTATS 2019poster

We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different reso…

Cited by 12Source ↗PDF ↗Scholar ↗
2019

Latent Space Autoregression for Novelty Detection

Davide Abati, Angelo Porrello, Simone Calderara, Rita Cucchiara
CVPR 2019poster

Novelty detection is commonly referred as the discrimination of observations that do not conform to a learned model of regularity. Despite its importance in different application settings, designing a novelty detector is utterly complex due to the unpredictable nature of novelties and its inaccessib…

Cited by 619PDF ↗code ↗Scholar ↗
2018

Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World

Matteo Fabbri, Fabio Lanzi, Simone Calderara, Andrea Palazzi, Roberto Vezzani, Rita Cucchiara
ECCV 2018poster

Multi-People Tracking in an open-world setting requires a special effort in precise detection. Moreover, temporal continuity in the detection phase gains more importance when scene cluttering introduces the challenging problems of occluded targets. For the purpose, we propose a deep network architec…

Cited by 226Source ↗PDF ↗Scholar ↗