arXiv subjects

Bertrand Le Saux

Publications and source records attributed to Bertrand Le Saux.

At least 19 recordsLinked to original sources

arXiv2026

Scaling Laws for Geospatial Foundation Models: A case study on PhilEO Bench

Foundation Models (FMs) have achieved state-of-the-art performance across domains by leveraging large-scale pretraining. In Earth Observation (EO), the availability of petabyte-scale satellite archives has recently enabled the development of GeoSpatial Foundation Models (GFMs). Yet, fundamental questions remain regarding how dataset size, model architecture, and size interact to determine downstream performance. In this work, we systematically explore this design space by pretraining and fine-tuning models on three dataset scales: PhilEO Globe (0.5TB), FastTOM (2TB, introduced here), and MajorTOM (23TB). We evaluate three architectural families: Geo-Aware U-Net (CNN), ViT-UPerNet (Transformer), and Mamba (State-Space Model); across model sizes ranging from 44M to 300M parameters. All models are benchmarked on the PhilEO Bench, covering: road density and building density regression, and land cover segmentation, and are compared against existing GFMs such as TerraMind and Prithvi-EO-2.0. Our results show that CNN-based models remain highly competitive in low-shot settings, with a 200M-parameter Geo-Aware U-Net outperforming larger architectures on regression tasks. However, when scaling to multi-terabyte datasets, ViT-UPerNet achieves the best performance, particularly for semantic segmentation on MajorTOM (23TB). Finally, we provide the first extensive evaluation of Mamba models in EO, highlighting their potential efficiency advantages, though further large-scale pretraining is required to fully match CNNs and ViTs. All code, pretrained models, and the FastTOM dataset are released publicly, enabling reproducibility and further exploration of scaling laws for GFMs.

cs.CV↗

arXiv2026

Quantum Circuit-Based Learning Models: Bridging Quantum Computing and Machine Learning

Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.

quant-ph↗

arXiv2025

Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation

Earth observation (EO) in open-world settings presents a unique challenge: different applications rely on diverse sensor modalities, each with varying ground sampling distances, spectral ranges, and numbers of spectral bands. However, existing EO foundation models are typically tailored to specific sensor types, making them inflexible when generalizing across the heterogeneous landscape of EO data. To address this, we propose the Dynamic One-For-All (DOFA) model, a unified, multimodal foundation framework designed for diverse vision tasks in EO. Inspired by neural plasticity, DOFA utilizes a wavelength-conditioned dynamic hypernetwork to process inputs from five distinct satellite sensors flexibly. By continually pretraining on five EO modalities, DOFA achieves state-of-the-art performance across multiple downstream tasks and generalizes well to unseen modalities. Enhanced with hybrid continual pretraining, DOFA+ requires significantly fewer computational resources while outperforming counterparts trained with extensive GPU budgets. Experiments on diverse datasets highlight DOFA's potential as a foundation for general-purpose vision models in the sensor-diverse EO domain. The code and pre-trained weights are publicly available at https://github.com/zhu-xlab/DOFA.

cs.CV↗

arXiv2025

Quantum Latent Diffusion Models

The introduction of quantum concepts is increasingly making its way into generative machine learning models. However, while there are various implementations of quantum Generative Adversarial Networks, the integration of quantum elements into diffusion models remains an open and challenging task. In this work, we propose a potential version of a quantum diffusion model that leverages the established idea of classical latent diffusion models. This involves using a traditional autoencoder to reduce images, followed by operations with variational circuits in the latent space. To effectively assess the benefits brought by quantum computing, the images generated by the quantum latent diffusion model have been compared to those generated by a classical model with a similar number of parameters, evaluated in terms of quantitative metrics. The results demonstrate an advantage in using a quantum version, as evidenced by obtaining better metrics for the images generated by the quantum version compared to those obtained by the classical version. Furthermore, quantum models continue to outperform even when considering small percentages of the dataset for training, demonstrating the quantum's ability to extract features more effectively even in a few shot learning scenario.

quant-ph↗

arXiv2024

IceCloudNet: 3D reconstruction of cloud ice from Meteosat SEVIRI

IceCloudNet is a novel method based on machine learning able to predict high-quality vertically resolved cloud ice water contents (IWC) and ice crystal number concentrations (N$_\textrm{ice}$). The predictions come at the spatio-temporal coverage and resolution of geostationary satellite observations (SEVIRI) and the vertical resolution of active satellite retrievals (DARDAR). IceCloudNet consists of a ConvNeXt-based U-Net and a 3D PatchGAN discriminator model and is trained by predicting DARDAR profiles from co-located SEVIRI images. Despite the sparse availability of DARDAR data due to its narrow overpass, IceCloudNet is able to predict cloud occurrence, spatial structure, and microphysical properties with high precision. The model has been applied to ten years of SEVIRI data, producing a dataset of vertically resolved IWC and N$_\textrm{ice}$ of clouds containing ice with a 3 kmx3 kmx240 mx15 minute resolution in a spatial domain of 30°W to 30°E and 30°S to 30°N. The produced dataset increases the availability of vertical cloud profiles, for the period when DARDAR is available, by more than six orders of magnitude and moreover, IceCloudNet is able to produce vertical cloud profiles beyond the lifetime of the recently ended satellite missions underlying DARDAR.

physics.ao-ph↗

arXiv2024

Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward

Earth observation (EO) is a prime instrument for monitoring land and ocean processes, studying the dynamics at work, and taking the pulse of our planet. This article gives a bird's eye view of the essential scientific tools and approaches informing and supporting the transition from raw EO data to usable EO-based information. The promises, as well as the current challenges of these developments, are highlighted under dedicated sections. Specifically, we cover the impact of (i) Computer vision; (ii) Machine learning; (iii) Advanced processing and computing; (iv) Knowledge-based AI; (v) Explainable AI and causal inference; (vi) Physics-aware models; (vii) User-centric approaches; and (viii) the much-needed discussion of ethical and societal issues related to the massive use of ML technologies in EO.

cs.CV↗

arXiv2024

Estimating optical vegetation indices and biophysical variables for temperate forests with Sentinel-1 SAR data using machine learning techniques: A case study for Czechia

Current optical vegetation indices (VIs) for monitoring forest ecosystems are well established and widely used in various applications, but can be limited by atmospheric effects such as clouds. In contrast, synthetic aperture radar (SAR) data can offer insightful and systematic forest monitoring with complete time series (TS) due to signal penetration through clouds and day and night image acquisitions. This study aims to address the limitations of optical satellite data by using SAR data as an alternative for estimating optical VIs for forests through machine learning (ML). While this approach is less direct and likely only feasible through the power of ML, it raises the scientific question of whether enough relevant information is contained in the SAR signal to accurately estimate VIs. This work covers the estimation of TS of four VIs (LAI, FAPAR, EVI and NDVI) using multitemporal Sentinel-1 SAR and ancillary data. The study focused on both healthy and disturbed temperate forest areas in Czechia for the year 2021, while ground truth labels generated from Sentinel-2 multispectral data. This was enabled by creating a paired multi-modal TS dataset in Google Earth Engine (GEE), including temporally and spatially aligned Sentinel-1, Sentinel-2, DEM, weather and land cover datasets. The inclusion of DEM-derived auxiliary features and additional meteorological information, further improved the results. In the comparison of ML models, the traditional ML algorithms, RFR and XGBoost slightly outperformed the AutoML approach, auto-sklearn, for all VIs, achieving high accuracies ($R^2$ between 70-86%) and low errors (0.055-0.29 of MAE). In general, up to 240 measurements per year and a spatial resolution of 20 m can be achieved using estimated SAR-based VIs with high accuracy. A great advantage of the SAR-based VI is the ability to detect abrupt forest changes with sub-weekly temporal accuracy.

stat.ML↗

arXiv2024

From Graphs to Qubits: A Critical Review of Quantum Graph Neural Networks

Quantum Graph Neural Networks (QGNNs) represent a novel fusion of quantum computing and Graph Neural Networks (GNNs), aimed at overcoming the computational and scalability challenges inherent in classical GNNs that are powerful tools for analyzing data with complex relational structures but suffer from limitations such as high computational complexity and over-smoothing in large-scale applications. Quantum computing, leveraging principles like superposition and entanglement, offers a pathway to enhanced computational capabilities. This paper critically reviews the state-of-the-art in QGNNs, exploring various architectures. We discuss their applications across diverse fields such as high-energy physics, molecular chemistry, finance and earth sciences, highlighting the potential for quantum advantage. Additionally, we address the significant challenges faced by QGNNs, including noise, decoherence, and scalability issues, proposing potential strategies to mitigate these problems. This comprehensive review aims to provide a foundational understanding of QGNNs, fostering further research and development in this promising interdisciplinary field.

quant-ph↗

arXiv2024

Quanv4EO: Empowering Earth Observation by means of Quanvolutional Neural Networks

A significant amount of remotely sensed data is generated daily by many Earth observation (EO) spaceborne and airborne sensors over different countries of our planet. Different applications use those data, such as natural hazard monitoring, global climate change, urban planning, and more. Many challenges are brought by the use of these big data in the context of remote sensing applications. In recent years, employment of machine learning (ML) and deep learning (DL)-based algorithms have allowed a more efficient use of these data but the issues in managing, processing, and efficiently exploiting them have even increased since classical computers have reached their limits. This article highlights a significant shift towards leveraging quantum computing techniques in processing large volumes of remote sensing data. The proposed Quanv4EO model introduces a quanvolution method for preprocessing multi-dimensional EO data. First its effectiveness is demonstrated through image classification tasks on MNIST and Fashion MNIST datasets, and later on, its capabilities on remote sensing image classification and filtering are shown. Key findings suggest that the proposed model not only maintains high precision in image classification but also shows improvements of around 5\% in EO use cases compared to classical approaches. Moreover, the proposed framework stands out for its reduced parameter size and the absence of training quantum kernels, enabling better scalability for processing massive datasets. These advancements underscore the promising potential of quantum computing in addressing the limitations of classical algorithms in remote sensing applications, offering a more efficient and effective alternative for image data classification and analysis.

eess.IV↗

arXiv2024

In Search of Quantum Advantage: Estimating the Number of Shots in Quantum Kernel Methods

Quantum Machine Learning (QML) has gathered significant attention through approaches like Quantum Kernel Machines. While these methods hold considerable promise, their quantum nature presents inherent challenges. One major challenge is the limited resolution of estimated kernel values caused by the finite number of circuit runs performed on a quantum device. In this study, we propose a comprehensive system of rules and heuristics for estimating the required number of circuit runs in quantum kernel methods. We introduce two critical effects that necessitate an increased measurement precision through additional circuit runs: the spread effect and the concentration effect. The effects are analyzed in the context of fidelity and projected quantum kernels. To address these phenomena, we develop an approach for estimating desired precision of kernel values, which, in turn, is translated into the number of circuit runs. Our methodology is validated through extensive numerical simulations, focusing on the problem of exponential value concentration. We stress that quantum kernel methods should not only be considered from the machine learning performance perspective, but also from the context of the resource consumption. The results provide insights into the possible benefits of quantum kernel methods, offering a guidance for their application in quantum machine learning tasks.

quant-ph↗

arXiv2024

Evaluating and Benchmarking Foundation Models for Earth Observation and Geospatial AI

When we are primarily interested in solving several problems jointly with a given prescribed high performance accuracy for each target application, then Foundation Models should for most cases be used rather than problem-specific models. We focus on the specific Computer Vision application of Foundation Models for Earth Observation (EO) and geospatial AI. These models can solve important problems we are tackling, including for example land cover classification, crop type mapping, flood segmentation, building density estimation, and road regression segmentation. In this paper, we show that for a limited number of labelled data, Foundation Models achieve improved performance compared to problem-specific models. In this work, we also present our proposed evaluation benchmark for Foundation Models for EO. Benchmarking the generalization performance of Foundation Models is important as it has become difficult to standardize a fair comparison across the many different models that have been proposed recently. We present the results using our evaluation benchmark for EO Foundation Models and show that Foundation Models are label efficient in the downstream tasks and help us solve problems we are tackling in EO and remote sensing.

cs.CV↗

arXiv2024

Latent Style-based Quantum GAN for high-quality Image Generation

Quantum generative modeling is among the promising candidates for achieving a practical advantage in data analysis. Nevertheless, one key challenge is to generate large-size images comparable to those generated by their classical counterparts. In this work, we take an initial step in this direction and introduce the Latent Style-based Quantum GAN (LaSt-QGAN), which employs a hybrid classical-quantum approach in training Generative Adversarial Networks (GANs) for arbitrary complex data generation. This novel approach relies on powerful classical auto-encoders to map a high-dimensional original image dataset into a latent representation. The hybrid classical-quantum GAN operates in this latent space to generate an arbitrary number of fake features, which are then passed back to the auto-encoder to reconstruct the original data. Our LaSt-QGAN can be successfully trained on realistic computer vision datasets beyond the standard MNIST, namely Fashion MNIST (fashion products) and SAT4 (Earth Observation images) with 10 qubits, resulting in a comparable performance (and even better in some metrics) with the classical GANs. Moreover, we analyze the barren plateau phenomena within this context of the continuous quantum generative model using a polynomial depth circuit and propose a method to mitigate the detrimental effect during the training of deep-depth networks. Through empirical experiments and theoretical analysis, we demonstrate the potential of LaSt-QGAN for the practical usage in the context of image generation and open the possibility of applying it to a larger dataset in the future.

quant-ph↗

arXiv2024

A Semantic Segmentation-guided Approach for Ground-to-Aerial Image Matching

Nowadays the accurate geo-localization of ground-view images has an important role across domains as diverse as journalism, forensics analysis, transports, and Earth Observation. This work addresses the problem of matching a query ground-view image with the corresponding satellite image without GPS data. This is done by comparing the features from a ground-view image and a satellite one, innovatively leveraging the corresponding latter's segmentation mask through a three-stream Siamese-like network. The proposed method, Semantic Align Net (SAN), focuses on limited Field-of-View (FoV) and ground panorama images (images with a FoV of 360°). The novelty lies in the fusion of satellite images in combination with their semantic segmentation masks, aimed at ensuring that the model can extract useful features and focus on the significant parts of the images. This work shows how SAN through semantic analysis of images improves the performance on the unlabelled CVUSA dataset for all the tested FoVs.

cs.CV↗

arXiv2024

Learning from Unlabelled Data with Transformers: Domain Adaptation for Semantic Segmentation of High Resolution Aerial Images

Data from satellites or aerial vehicles are most of the times unlabelled. Annotating such data accurately is difficult, requires expertise, and is costly in terms of time. Even if Earth Observation (EO) data were correctly labelled, labels might change over time. Learning from unlabelled data within a semi-supervised learning framework for segmentation of aerial images is challenging. In this paper, we develop a new model for semantic segmentation of unlabelled images, the Non-annotated Earth Observation Semantic Segmentation (NEOS) model. NEOS performs domain adaptation as the target domain does not have ground truth semantic segmentation masks. The distribution inconsistencies between the target and source domains are due to differences in acquisition scenes, environment conditions, sensors, and times. Our model aligns the learned representations of the different domains to make them coincide. The evaluation results show that NEOS is successful and outperforms other models for semantic segmentation of unlabelled data.

cs.CV↗

arXiv2024

Towards Efficient Quantum Hybrid Diffusion Models

In this paper, we propose a new methodology to design quantum hybrid diffusion models, derived from classical U-Nets with ResNet and Attention layers. Specifically, we propose two possible different hybridization schemes combining quantum computing's superior generalization with classical networks' modularity. In the first one, we acted at the vertex: ResNet convolutional layers are gradually replaced with variational circuits to create Quantum ResNet blocks. In the second proposed architecture, we extend the hybridization to the intermediate level of the encoder, due to its higher sensitivity in the feature extraction process. In order to conduct an in-depth analysis of the potential advantages stemming from the integration of quantum layers, images generated by quantum hybrid diffusion models are compared to those generated by classical models, and evaluated in terms of several quantitative metrics. The results demonstrate an advantage in using a hybrid quantum diffusion models, as they generally synthesize better-quality images and converges faster. Moreover, they show the additional advantage of having a lower number of parameters to train compared to the classical one, with a reduction that depends on the extent to which the vertex is hybridized.

quant-ph↗

arXiv2024

A Hybrid MLP-Quantum approach in Graph Convolutional Neural Networks for Oceanic Nino Index (ONI) prediction

This paper explores an innovative fusion of Quantum Computing (QC) and Artificial Intelligence (AI) through the development of a Hybrid Quantum Graph Convolutional Neural Network (HQGCNN), combining a Graph Convolutional Neural Network (GCNN) with a Quantum Multilayer Perceptron (MLP). The study highlights the potentialities of GCNNs in handling global-scale dependencies and proposes the HQGCNN for predicting complex phenomena such as the Oceanic Nino Index (ONI). Preliminary results suggest the model potential to surpass state-of-the-art (SOTA). The code will be made available with the paper publication.

eess.SP↗

arXiv2024

PhilEO Bench: Evaluating Geo-Spatial Foundation Models

Massive amounts of unlabelled data are captured by Earth Observation (EO) satellites, with the Sentinel-2 constellation generating 1.6 TB of data daily. This makes Remote Sensing a data-rich domain well suited to Machine Learning (ML) solutions. However, a bottleneck in applying ML models to EO is the lack of annotated data as annotation is a labour-intensive and costly process. As a result, research in this domain has focused on Self-Supervised Learning and Foundation Model approaches. This paper addresses the need to evaluate different Foundation Models on a fair and uniform benchmark by introducing the PhilEO Bench, a novel evaluation framework for EO Foundation Models. The framework comprises of a testbed and a novel 400 GB Sentinel-2 dataset containing labels for three downstream tasks, building density estimation, road segmentation, and land cover classification. We present experiments using our framework evaluating different Foundation Models, including Prithvi and SatMAE, at multiple n-shots and convergence rates.

cs.CV↗

arXiv2023

The curse of language biases in remote sensing VQA: the role of spatial attributes, language diversity, and the need for clear evaluation

Remote sensing visual question answering (RSVQA) opens new opportunities for the use of overhead imagery by the general public, by enabling human-machine interaction with natural language. Building on the recent advances in natural language processing and computer vision, the goal of RSVQA is to answer a question formulated in natural language about a remote sensing image. Language understanding is essential to the success of the task, but has not yet been thoroughly examined in RSVQA. In particular, the problem of language biases is often overlooked in the remote sensing community, which can impact model robustness and lead to wrong conclusions about the performances of the model. Thus, the present work aims at highlighting the problem of language biases in RSVQA with a threefold analysis strategy: visual blind models, adversarial testing and dataset analysis. This analysis focuses both on model and data. Moreover, we motivate the use of more informative and complementary evaluation metrics sensitive to the issue. The gravity of language biases in RSVQA is then exposed for all of these methods with the training of models discarding the image data and the manipulation of the visual input during inference. Finally, a detailed analysis of question-answer distribution demonstrates the root of the problem in the data itself. Thanks to this analytical study, we observed that biases in remote sensing are more severe than in standard VQA, likely due to the specifics of existing remote sensing datasets for the task, e.g. geographical similarities and sparsity, as well as a simpler vocabulary and question generation strategies. While new, improved and less-biased datasets appear as a necessity for the development of the promising field of RSVQA, we demonstrate that more informed, relative evaluation metrics remain much needed to transparently communicate results of future RSVQA methods.

cs.CV↗