arXiv subjects

Lorenzo Papa

Publications and source records attributed to Lorenzo Papa.

13 recordsLinked to original sources

arXiv2026

Remote entanglement of massive oscillators via wire-mediated Coulomb interaction

We propose a method to enhance Coulomb interaction between charged macroscopic mechanical oscillators by placing a conducting structure in their vicinity. We derive the effective motional dynamics of the two oscillators using macroscopic quantum electrodynamics and show that image charges induced in the conductor fundamentally modify the range of the electrostatic interaction. For the specific case of a cylindrical wire, we predict that the coherent motional coupling changes from the free-space scaling $1/D^3$ to an asymptotic $1/(D\ln^2 D)$ dependence on the separation $D$ between the oscillators, at the cost of only negligible additional decoherence for low-frequency oscillators. We further show that, when combined with continuous position measurements, the enhanced interaction enables the generation of steady-state motional entanglement between the oscillators over significantly larger distances than achievable in free space. For experimentally realistic milligram-scale oscillators, we predict observable entanglement at separations of several hundred microns -- more than an order of magnitude beyond free-space capabilities -- with improvements approaching two orders of magnitude in future systems. These results identify conductor-assisted Coulomb interactions as a resource for quantum control of massive objects and for the exploration of entanglement generated by fundamental central forces.

quant-ph↗

arXiv2025

Enriching Earth Observation labeled data with Quantum Conditioned Diffusion Models

The rapid adoption of diffusion models (DMs) in the Earth Observation (EO) domain has unlocked new generative capabilities aimed at producing new samples, whose statistical properties closely match real imagery, for tasks such as synthesizing missing data, augmenting scarce labeled datasets, and improving image reconstruction. This is particularly relevant in EO, where labeled data are often costly to obtain and limited in availability. However, classical DMs still face significant computational limitations, requiring hundreds to thousands of inference steps, as well as difficulties in capturing the intricate spatial and spectral correlations characteristic of EO data. Recent research in Quantum Machine Learning (QML), including initial attempts of Quantum Generative Models, offers a fundamentally different approach to overcome these challenges. Motivated by these considerations, we introduce the Quanvolutional Conditioned U-Net (QCU-Net), a hybrid quantum--classical architecture that applies quantum operations within a conditioned diffusion framework using a novel quanvolutional feature-extraction approach, for generating synthetic labeled EO imagery. Extensive experiments on the EuroSAT RGB dataset demonstrate that our QCU-Net achieves superior results. Notably, it reduces the Fréchet Inception Distance by 64%, lowers the Kernel Inception Distance by 76%, and yields higher semantic accuracy. Ablation studies further reveal that strategically positioning quantum layers and employing entangling variational circuits enhance model performance and convergence. This work represents the first successful adaptation of class-conditioned quantum diffusion modeling in the EO domain, paving the way for quantum-enhanced remote sensing imagery synthesis.

quant-ph↗

arXiv2025

VidCLearn: A Continual Learning Approach for Text-to-Video Generation

Text-to-video generation is an emerging field in generative AI, enabling the creation of realistic, semantically accurate videos from text prompts. While current models achieve impressive visual quality and alignment with input text, they typically rely on static knowledge, making it difficult to incorporate new data without retraining from scratch. To address this limitation, we propose VidCLearn, a continual learning framework for diffusion-based text-to-video generation. VidCLearn features a student-teacher architecture where the student model is incrementally updated with new text-video pairs, and the teacher model helps preserve previously learned knowledge through generative replay. Additionally, we introduce a novel temporal consistency loss to enhance motion smoothness and a video retrieval module to provide structural guidance at inference. Our architecture is also designed to be more computationally efficient than existing models while retaining satisfactory generation performance. Experimental results show VidCLearn's superiority over baseline methods in terms of visual quality, semantic alignment, and temporal coherence.

cs.CV↗

arXiv2025

Shedding Light on Depth: Explainability Assessment in Monocular Depth Estimation

Explainable artificial intelligence is increasingly employed to understand the decision-making process of deep learning models and create trustworthiness in their adoption. However, the explainability of Monocular Depth Estimation (MDE) remains largely unexplored despite its wide deployment in real-world applications. In this work, we study how to analyze MDE networks to map the input image to the predicted depth map. More in detail, we investigate well-established feature attribution methods, Saliency Maps, Integrated Gradients, and Attention Rollout on different computationally complex models for MDE: METER, a lightweight network, and PixelFormer, a deep network. We assess the quality of the generated visual explanations by selectively perturbing the most relevant and irrelevant pixels, as identified by the explainability methods, and analyzing the impact of these perturbations on the model's output. Moreover, since existing evaluation metrics can have some limitations in measuring the validity of visual explanations for MDE, we additionally introduce the Attribution Fidelity. This metric evaluates the reliability of the feature attribution by assessing their consistency with the predicted depth map. Experimental results demonstrate that Saliency Maps and Integrated Gradients have good performance in highlighting the most important input features for MDE lightweight and deep models, respectively. Furthermore, we show that Attribution Fidelity effectively identifies whether an explainability method fails to produce reliable visual maps, even in scenarios where conventional metrics might suggest satisfactory results.

cs.CV↗

arXiv2025

Enhancing Ground-to-Aerial Image Matching for Visual Misinformation Detection Using Semantic Segmentation

The recent advancements in generative AI techniques, which have significantly increased the online dissemination of altered images and videos, have raised serious concerns about the credibility of digital media available on the Internet and distributed through information channels and social networks. This issue particularly affects domains that rely heavily on trustworthy data, such as journalism, forensic analysis, and Earth observation. To address these concerns, the ability to geolocate a non-geo-tagged ground-view image without external information, such as GPS coordinates, has become increasingly critical. This study tackles the challenge of linking a ground-view image, potentially exhibiting varying fields of view (FoV), to its corresponding satellite image without the aid of GPS data. To achieve this, we propose a novel four-stream Siamese-like architecture, the Quadruple Semantic Align Net (SAN-QUAD), which extends previous state-of-the-art (SOTA) approaches by leveraging semantic segmentation applied to both ground and satellite imagery. Experimental results on a subset of the CVUSA dataset demonstrate significant improvements of up to 9.8% over prior methods across various FoV settings.

cs.CV↗

arXiv2024

Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization

Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory requirements for elements like moving averages and a poorly understood convergence theory. To overcome these challenges, we introduce F-CMA, a Fast-Controlled Mini-batch Algorithm with a random reshuffling method featuring a sufficient decrease condition and a line-search procedure to ensure loss reduction per epoch, along with its deterministic proof of global convergence to a stationary point. To evaluate the F-CMA, we integrate it into conventional training protocols for classification tasks involving both convolutional neural networks and vision transformer models, allowing for a direct comparison with popular optimizers. Computational tests show significant improvements, including a decrease in the overall training time by up to 68%, an increase in per-epoch efficiency by up to 20%, and in model accuracy by up to 5%.

cs.LG↗

arXiv2024

On the impact of key design aspects in simulated Hybrid Quantum Neural Networks for Earth Observation

Quantum computing has introduced novel perspectives for tackling and improving machine learning tasks. Moreover, the integration of quantum technologies together with well-known deep learning (DL) architectures has emerged as a potential research trend gaining attraction across various domains, such as Earth Observation (EO) and many other research fields. However, prior related works in EO literature have mainly focused on convolutional architectural advancements, leaving several essential topics unexplored. Consequently, this research investigates through three cases of study fundamental aspects of hybrid quantum machine models for EO tasks aiming to provide a solid groundwork for future research studies towards more adequate simulations and looking at the post-NISQ era. More in detail, we firstly (1) investigate how different quantum libraries behave when training hybrid quantum models, assessing their computational efficiency and effectiveness. Secondly, (2) we analyze the stability/sensitivity to initialization values (i.e., seed values) in both traditional model and quantum-enhanced counterparts. Finally, (3) we explore the benefits of hybrid quantum attention-based models in EO applications, examining how integrating quantum circuits into ViTs can improve model performance.

quant-ph↗

arXiv2024

Computational issues in Optimization for Deep networks

The paper aims to investigate relevant computational issues of deep neural network architectures with an eye to the interaction between the optimization algorithm and the classification performance. In particular, we aim to analyze the behaviour of state-of-the-art optimization algorithms in relationship to their hyperparameters setting in order to detect robustness with respect to the choice of a certain starting point in ending on different local solutions. We conduct extensive computational experiments using nine open-source optimization algorithms to train deep Convolutional Neural Network architectures on an image multi-class classification task. Precisely, we consider several architectures by changing the number of layers and neurons per layer, in order to evaluate the impact of different width and depth structures on the computational optimization performance.

math.OC↗

arXiv2024

A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism, outperforming earlier convolutional neural networks. However, ViT deployment and performance have grown steadily with their size, number of trainable parameters, and operations. Furthermore, self-attention's computational and memory cost quadratically increases with the image resolution. Generally speaking, it is challenging to employ these architectures in real-world applications due to many hardware and environmental restrictions, such as processing and computational capabilities. Therefore, this survey investigates the most efficient methodologies to ensure sub-optimal estimation performances. More in detail, four efficient categories will be analyzed: compact architecture, pruning, knowledge distillation, and quantization strategies. Moreover, a new metric called Efficient Error Rate has been introduced in order to normalize and compare models' features that affect hardware devices at inference time, such as the number of parameters, bits, FLOPs, and model size. Summarizing, this paper firstly mathematically defines the strategies used to make Vision Transformer efficient, describes and discusses state-of-the-art methodologies, and analyzes their performances over different application scenarios. Toward the end of this paper, we also discuss open challenges and promising research directions.

cs.CV↗

arXiv2024

Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It

Fake news detection models are critical to countering disinformation but can be manipulated through adversarial attacks. In this position paper, we analyze how an attacker can compromise the performance of an online learning detector on specific news content without being able to manipulate the original target news. In some contexts, such as social networks, where the attacker cannot exert complete control over all the information, this scenario can indeed be quite plausible. Therefore, we show how an attacker could potentially introduce poisoning data into the training data to manipulate the behavior of an online learning method. Our initial findings reveal varying susceptibility of logistic regression models based on complexity and attack type.

cs.LG↗

arXiv2023

Deep-Learning-based Change Detection with Spaceborne Hyperspectral PRISMA data

Change detection (CD) methods have been applied to optical data for decades, while the use of hyperspectral data with a fine spectral resolution has been rarely explored. CD is applied in several sectors, such as environmental monitoring and disaster management. Thanks to the PRecursore IperSpettrale della Missione operativA (PRISMA), hyperspectral-from-space CD is now possible. In this work, we apply standard and deep-learning (DL) CD methods to different targets, from natural to urban areas. We propose a pipeline starting from coregistration, followed by CD with a full-spectrum algorithm and by a DL network developed for optical data. We find that changes in vegetation and built environments are well captured. The spectral information is valuable to identify subtle changes and the DL methods are less affected by noise compared to the statistical method, but atmospheric effects and the lack of reliable ground truth represent a major challenge to hyperspectral CD.

cs.CV↗

arXiv2022

Automated Real-Space Lattice Extraction for Atomic Force Microscopy Images

Analyzing atomically resolved images is a time-consuming process requiring solid experience and substantial human intervention. In addition, the acquired images contain a large amount of information such as crystal structure, presence and distribution of defects, and formation of domains, which need to be resolved to understand a material's surface structure. Therefore, machine learning techniques have been applied in scanning probe and electron microscopies during the last years, aiming for automatized and efficient image analysis. This work introduces a free and open source tool (AiSurf: Automated Identification of Surface Images) developed to inspect atomically resolved images via Scale-Invariant Feature Transform (SIFT) and Clustering Algorithms (CA). AiSurf extracts primitive lattice vectors, unit cells, and structural distortions from the original image, with no pre-assumption on the lattice and minimal user intervention. The method is applied to various atomically resolved non-contact atomic force microscopy (AFM) images of selected surfaces with different levels of complexity: anatase TiO2(101), oxygen deficient rutile TiO2(110) with and without CO adsorbates, SrTiO3(001) with Sr vacancies and graphene with C vacancies. The code delivers excellent results and has proved to be robust against atom misclassification and noise, thereby facilitating the interpretation scanning probe microscopy images.

cond-mat.mtrl-sci↗

arXiv2022

DepthFake: a depth-based strategy for detecting Deepfake videos

Fake content has grown at an incredible rate over the past few years. The spread of social media and online platforms makes their dissemination on a large scale increasingly accessible by malicious actors. In parallel, due to the growing diffusion of fake image generation methods, many Deep Learning-based detection techniques have been proposed. Most of those methods rely on extracting salient features from RGB images to detect through a binary classifier if the image is fake or real. In this paper, we proposed DepthFake, a study on how to improve classical RGB-based approaches with depth-maps. The depth information is extracted from RGB images with recent monocular depth estimation techniques. Here, we demonstrate the effective contribution of depth-maps to the deepfake detection task on robust pre-trained architectures. The proposed RGBD approach is in fact able to achieve an average improvement of 3.20% and up to 11.7% for some deepfake attacks with respect to standard RGB architectures over the FaceForensic++ dataset.

cs.CV↗