6 papers
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…
Mitigating Negative Flips via Margin Preserving Training
Simone Ricci, Niccolò Biondi, Niccolò Biondi +2
Minimizing inconsistencies across successive versions of an AI system is as crucial as reducing the overall error. In image classification, such inconsistencies manifest as negativ…
-Orthogonality Regularization for Compatible Representation Learning
Simone Ricci, Niccolò Biondi, Niccolò Biondi +3
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…
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
Lorenzo Agnolucci, Alberto Baldrati, Alberto Del Bimbo +1
Given a query consisting of a reference image and a relative caption, Composed Image Retrieval (CIR) aims to retrieve target images visually similar to the reference one while inco…
Spike-TBR: a Noise Resilient Neuromorphic Event Representation
Gabriele Magrini, Federico Becattini, Luca Cultrera +3
Event cameras offer significant advantages over traditional frame-based sensors, including higher temporal resolution, lower latency and dynamic range. However, efficiently convert…
FRED: The Florence RGB-Event Drone Dataset
Gabriele Magrini, Niccolò Marini, Federico Becattini +4
Small, fast, and lightweight drones present significant challenges for traditional RGB cameras due to their limitations in capturing fast-moving objects, especially under challengi…