122 citations · 483 across the 70 of their papers we have counts for
6 papers · 1 filter
A Stationary (and Therefore Compatible) Representation is All You Need
Niccolò Biondi, Federico Pernici, Simone Ricci +1
Learning compatible representations aims to learn feature representations that can be used interchangeably over time whenever a model undergoes updates. In this paper, we demonstra…
-Orthogonality Regularization for Compatible Representation Learning
Simone Ricci, Niccolò Biondi, Federico Pernici +2
Retrieval systems rely on representations learned by increasingly powerful models. However, due to the high training cost and inconsistencies in learned representations, there is s…
DiffDefense: Defending against Adversarial Attacks via Diffusion Models
Hondamunige Prasanna Silva, Lorenzo Seidenari, Alberto Del Bimbo
This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any mod…
Regular Polytope Networks
Federico Pernici, Matteo Bruni, Claudio Baecchi +1
Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such…
Class-incremental Learning with Pre-allocated Fixed Classifiers
Federico Pernici, Matteo Bruni, Claudio Baecchi +2
In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural networks are known to suffer…
Text-to-Image Synthesis Based on Machine Generated Captions
Marco Menardi, Alex Falcon, Saida S. Mohamed +4
Text to Image Synthesis refers to the process of automatic generation of a photo-realistic image starting from a given text and is revolutionizing many real-world applications. In…