33 citations · 117 across the 14 of their papers we have counts for
18 papers
Spherical Interpolation for Backward-Compatible Multimodal Representations
Simone Ricci, Niccolò Biondi, Federico Pernici
Contrastive vision-language models map visual and textual representations into a shared normalized embedding space, making cosine similarity the natural metric for cross-modal retr…
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, Federico Pernici +1
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, 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…
Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
Simone Ricci, Niccolò Biondi, Federico Pernici +1
Visual retrieval systems face significant challenges when updating models with improved representations due to misalignment between the old and new representations. The costly and…
Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements
Niccolò Biondi, Federico Pernici, Simone Ricci +1
Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in search and retrieval syst…
Maximally Compact and Separated Features with Regular Polytope Networks
Federico Pernici, Matteo Bruni, Claudio Baecchi +1
Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks. Typically, a learnable transformation (i.e. the c…
CL2R: Compatible Lifelong Learning Representations
Niccolo Biondi, Federico Pernici, Matteo Bruni +2
In this paper, we propose a method to partially mimic natural intelligence for the problem of lifelong learning representations that are compatible. We take the perspective of a le…
Contrastive Supervised Distillation for Continual Representation Learning
Tommaso Barletti, Niccolo' Biondi, Federico Pernici +2
In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastro…
CoReS: Compatible Representations via Stationarity
Niccolo Biondi, Federico Pernici, Matteo Bruni +1
Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time. In visual search systems, this eliminates the need…
Fine-Grained Adversarial Semi-supervised Learning
Daniele Mugnai, Federico Pernici, Francesco Turchini +1
In this paper we exploit Semi-Supervised Learning (SSL) to increase the amount of training data to improve the performance of Fine-Grained Visual Categorization (FGVC). This proble…
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…
Temporal Binary Representation for Event-Based Action Recognition
Simone Undri Innocenti, Federico Becattini, Federico Pernici +1
In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms. The proposed meth…
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…
Fix Your Features: Stationary and Maximally Discriminative Embeddings using Regular Polytope (Fixed Classifier) 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…
Memory Based Online Learning of Deep Representations from Video Streams
Federico Pernici, Federico Bartoli, Matteo Bruni +1
We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechani…
Unsupervised Incremental Learning of Deep Descriptors From Video Streams
Federico Pernici, Alberto Del Bimbo
We present a novel unsupervised method for face identity learning from video sequences. The method exploits the ResNet deep network for face detection and VGGface fc7 face descript…
Continuous Localization and Mapping of a Pan Tilt Zoom Camera for Wide Area Tracking
Giuseppe Lisanti, Iacopo Masi, Federico Pernici +1
Pan-tilt-zoom (PTZ) cameras are powerful to support object identification and recognition in far-field scenes. However, the effective use of PTZ cameras in real contexts is complic…