Sylvain Lobry

Christel Chappuis, Eliot Walt, Vincent Mendez et al.

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.

Nicolas Houdré, Diego Marcos, Hugo Riffaud de Turckheim et al.

Earth observation (EO) data spans a wide range of spatial, spectral, and temporal resolutions, from high-resolution optical imagery to low resolution multispectral products or radar time series. While recent foundation models have improved multimodal integration for learning meaningful representations, they often expect fixed input resolutions or are based on sensor-specific encoders limiting generalization across heterogeneous EO modalities. To overcome these limitations we introduce RAMEN, a resolution-adjustable multimodal encoder that learns a shared visual representation across EO data in a fully sensor-agnostic manner. RAMEN treats the modality and spatial and temporal resolutions as key input data features, enabling coherent analysis across modalities within a unified latent space. Its main methodological contribution is to define spatial resolution as a controllable output parameter, giving users direct control over the desired level of detail at inference and allowing explicit trade-offs between spatial precision and computational cost. We train a single, unified transformer encoder reconstructing masked multimodal EO data drawn from diverse sources, ensuring generalization across sensors and resolutions. Once pretrained, RAMEN transfers effectively to both known and unseen sensor configurations and outperforms larger state-of-the-art models on the community-standard PANGAEA benchmark, containing various multi-sensor and multi-resolution downstream tasks. Our code and pretrained model are available at https://github.com/nicolashoudre/RAMEN.

Lucrezia Tosato, Hichem Boussaid, Flora Weissgerber et al.

Visual Question Answering for Remote Sensing (RSVQA) is a task that aims at answering natural language questions about the content of a remote sensing image. The visual features extraction is therefore an essential step in a VQA pipeline. By incorporating attention mechanisms into this process, models gain the ability to focus selectively on salient regions of the image, prioritizing the most relevant visual information for a given question. In this work, we propose to embed an attention mechanism guided by segmentation into a RSVQA pipeline. We argue that segmentation plays a crucial role in guiding attention by providing a contextual understanding of the visual information, underlying specific objects or areas of interest. To evaluate this methodology, we provide a new VQA dataset that exploits very high-resolution RGB orthophotos annotated with 16 segmentation classes and question/answer pairs. Our study shows promising results of our new methodology, gaining almost 10% of overall accuracy compared to a classical method on the proposed dataset.

Roger Ferrod, Maël Lecene, Krishna Sapkota et al.

Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical applications like urban planning, environmental monitoring and disaster management. However, Multimodal Large Language Models exhibit critical deficiencies in fine-grained spatial understanding within Remote Sensing, primarily due to a reliance on limited or repurposed legacy datasets. To bridge this gap, we introduce a large-scale dataset grounded in verifiable cadastral vector data, comprising 3.8 million annotated objects across 510k high-resolution images with 135 granular semantic categories. We validate this resource through a comprehensive instruction-tuning benchmark spanning seven spatial reasoning tasks. Our evaluation establishes a robust baseline using a standard LLaVA architecture. We show that while current RS-specialized and commercial models (e.g., Gemini) struggle in zero-shot settings, high-fidelity supervision effectively bridges this gap, enabling standard architectures to master fine-grained spatial grounding without complex architectural modifications.

Lucrezia Tosato, Sylvain Lobry, Flora Weissgerber et al.

Remote sensing visual question answering (RSVQA) has been involved in several research in recent years, leading to an increase in new methods. RSVQA automatically extracts information from satellite images, so far only optical, and a question to automatically search for the answer in the image and provide it in a textual form. In our research, we study whether Synthetic Aperture Radar (SAR) images can be beneficial to this field. We divide our study into three phases which include classification methods and VQA. In the first one, we explore the classification results of SAR alone and investigate the best method to extract information from SAR data. Then, we study the combination of SAR and optical data. In the last phase, we investigate how SAR images and a combination of different modalities behave in RSVQA compared to a method only using optical images. We conclude that adding the SAR modality leads to improved performances, although further research on using SAR data to automatically answer questions is needed as well as more balanced datasets.

Rebecca Leygonie, Sylvain Lobry, Laurent Wendling (LIPADE)

We wish to define the limits of a classical classification model based on deep learning when applied to abstract images, which do not represent visually identifiable objects.QR codes (Quick Response codes) fall into this category of abstract images: one bit corresponding to one encoded character, QR codes were not designed to be decoded manually. To understand the limitations of a deep learning-based model for abstract image classification, we train an image classification model on QR codes generated from information obtained when reading a health pass. We compare a classification model with a classical (deterministic) decoding method in the presence of noise. This study allows us to conclude that a model based on deep learning can be relevant for the understanding of abstract images.

Yuxing Chen, Weijie Wang, Sylvain Lobry et al.

Large language models (LLMs) are being used in data science code generation tasks, but they often struggle with complex sequential tasks, leading to logical errors. Their application to geospatial data processing is particularly challenging due to difficulties in incorporating complex data structures and spatial constraints, effectively utilizing diverse function calls, and the tendency to hallucinate less-used geospatial libraries. To tackle these problems, we introduce GeoAgent, a new interactive framework designed to help LLMs handle geospatial data processing more effectively. GeoAgent pioneers the integration of a code interpreter, static analysis, and Retrieval-Augmented Generation (RAG) techniques within a Monte Carlo Tree Search (MCTS) algorithm, offering a novel approach to geospatial data processing. In addition, we contribute a new benchmark specifically designed to evaluate the LLM-based approach in geospatial tasks. This benchmark leverages a variety of Python libraries and includes both single-turn and multi-turn tasks such as data acquisition, data analysis, and visualization. By offering a comprehensive evaluation among diverse geospatial contexts, this benchmark sets a new standard for developing LLM-based approaches in geospatial data analysis tasks. Our findings suggest that relying solely on knowledge of LLM is insufficient for accurate geospatial task programming, which requires coherent multi-step processes and multiple function calls. Compared to the baseline LLMs, the proposed GeoAgent has demonstrated superior performance, yielding notable improvements in function calls and task completion. In addition, these results offer valuable insights for the future development of LLM agents in automatic geospatial data analysis task programming.

Hichem Boussaid, Lucrezia Tosato, Flora Weissgerber et al.

The extraction of visual features is an essential step in Visual Question Answering (VQA). Building a good visual representation of the analyzed scene is indeed one of the essential keys for the system to be able to correctly understand the latter in order to answer complex questions. In many fields such as remote sensing, the visual feature extraction step could benefit significantly from leveraging different image modalities carrying complementary spectral, spatial and contextual information. In this work, we propose to add multiple image modalities to VQA in the particular context of remote sensing, leading to a novel task for the computer vision community. To this end, we introduce a new VQA dataset, named TAMMI (Text and Multi-Modal Imagery) with diverse questions on scenes described by three different modalities (very high resolution RGB, multi-spectral imaging data and synthetic aperture radar). Thanks to an automated pipeline, this dataset can be easily extended according to experimental needs. We also propose the MM-RSVQA (Multi-modal Multi-resolution Remote Sensing Visual Question Answering) model, based on VisualBERT, a vision-language transformer, to effectively combine the multiple image modalities and text through a trainable fusion process. A preliminary experimental study shows promising results of our methodology on this challenging dataset, with an accuracy of 65.56% on the targeted VQA task. This pioneering work paves the way for the community to a new multi-modal multi-resolution VQA task that can be applied in other imaging domains (such as medical imaging) where multi-modality can enrich the visual representation of a scene. The dataset and code are available at https://tammi.sylvainlobry.com/.

Lucrezia Tosato, Flora Weissgerber, Laurent Wendling et al.

Remote Sensing Visual Question Answering (RSVQA) is a task that extracts information from satellite images to answer questions in natural language, aiding image interpretation. While several methods exist for optical images with varying spectral bands and resolutions, only recently have high-resolution Synthetic Aperture Radar (SAR) images been explored. SAR's ability to operate in all weather conditions and capture electromagnetic features makes it a promising modality, yet no study has compared SAR and optical imagery in RSVQA or proposed effective fusion strategies. This work investigates how to integrate SAR data into RSVQA and how to best combine it with optical images. We present a dataset that enables SAR-based RSVQA and explore two pipelines for the task. The first is an end-to-end model, while the second is a two-stage framework: SAR information is first extracted and translated into text, which is then processed by a language model to produce the final answer. Our results show that the two-stage model performs better, improving accuracy by nearly 10% over the end-to-end approach. We also evaluate fusion strategies for combining SAR and optical data. A decision-level fusion yields the best results, with an F1-micro score of 75.00%, F1-average of 81.21%, and overall accuracy of 75.49% on the proposed dataset. SAR proves especially beneficial for questions related to specific land cover types, such as water areas, demonstrating its value as a complementary modality to optical imagery.

Lucrezia Tosato, Christel Tartini Chappuis, Syrielle Montariol et al.

Remote Sensing Visual Question Answering (RSVQA) presents unique challenges in ensuring that model decisions are both understandable and grounded in visual content. Current models often suffer from a lack of interpretability and explainability, as well as from biases in dataset distributions that lead to shortcut learning. In this work, we tackle these issues by introducing a novel RSVQA dataset, Chessboard, designed to minimize biases through 3'123'253 questions and a balanced answer distribution. Each answer is linked to one or more cells within the image, enabling fine-grained visual reasoning. Building on this dataset, we develop an explainable and interpretable model called Checkmate that identifies the image cells most relevant to its decisions. Through extensive experiments across multiple model architectures, we show that our approach improves transparency and supports more trustworthy decision-making in RSVQA systems.

Hugo Riffaud de Turckheim, Sylvain Lobry, Roberto Interdonato et al.

The growing number of Earth observation satellites has led to increasingly diverse remote sensing data, with varying spatial, spectral, and temporal configurations. Most existing models rely on fixed input formats and modality-specific encoders, which require retraining when new configurations are introduced, limiting their ability to generalize across modalities. We introduce Atomizer, a flexible architecture that represents remote sensing images as sets of scalars, each corresponding to a spectral band value of a pixel. Each scalar is enriched with contextual metadata (acquisition time, spatial resolution, wavelength, and bandwidth), producing an atomic representation that allows a single encoder to process arbitrary modalities without interpolation or resampling. Atomizer uses structured tokenization with Fourier features and non-uniform radial basis functions to encode content and context, and maps tokens into a latent space via cross-attention. Under modality-disjoint evaluations, Atomizer outperforms standard models and demonstrates robust performance across varying resolutions and spatial sizes.

Christel Chappuis, Sylvain Lobry, Benjamin Kellenberger et al.

Visual question answering (VQA) has recently been introduced to remote sensing to make information extraction from overhead imagery more accessible to everyone. VQA considers a question (in natural language, therefore easy to formulate) about an image and aims at providing an answer through a model based on computer vision and natural language processing methods. As such, a VQA model needs to jointly consider visual and textual features, which is frequently done through a fusion step. In this work, we study three different fusion methodologies in the context of VQA for remote sensing and analyse the gains in accuracy with respect to the model complexity. Our findings indicate that more complex fusion mechanisms yield an improved performance, yet that seeking a trade-of between model complexity and performance is worthwhile in practice.

Diego Marcos, Ruth Fong, Sylvain Lobry et al.

Convolutional neural networks (CNN) are known to learn an image representation that captures concepts relevant to the task, but do so in an implicit way that hampers model interpretability. However, one could argue that such a representation is hidden in the neurons and can be made explicit by teaching the model to recognize semantically interpretable attributes that are present in the scene. We call such an intermediate layer a \emph{semantic bottleneck}. Once the attributes are learned, they can be re-combined to reach the final decision and provide both an accurate prediction and an explicit reasoning behind the CNN decision. In this paper, we look into semantic bottlenecks that capture context: we want attributes to be in groups of a few meaningful elements and participate jointly to the final decision. We use a two-layer semantic bottleneck that gathers attributes into interpretable, sparse groups, allowing them contribute differently to the final output depending on the context. We test our contextual semantic interpretable bottleneck (CSIB) on the task of landscape scenicness estimation and train the semantic interpretable bottleneck using an auxiliary database (SUN Attributes). Our model yields in predictions as accurate as a non-interpretable baseline when applied to a real-world test set of Flickr images, all while providing clear and interpretable explanations for each prediction.

Sylvain Lobry, Diego Marcos, Jesse Murray et al.

This paper introduces the task of visual question answering for remote sensing data (RSVQA). Remote sensing images contain a wealth of information which can be useful for a wide range of tasks including land cover classification, object counting or detection. However, most of the available methodologies are task-specific, thus inhibiting generic and easy access to the information contained in remote sensing data. As a consequence, accurate remote sensing product generation still requires expert knowledge. With RSVQA, we propose a system to extract information from remote sensing data that is accessible to every user: we use questions formulated in natural language and use them to interact with the images. With the system, images can be queried to obtain high level information specific to the image content or relational dependencies between objects visible in the images. Using an automatic method introduced in this article, we built two datasets (using low and high resolution data) of image/question/answer triplets. The information required to build the questions and answers is queried from OpenStreetMap (OSM). The datasets can be used to train (when using supervised methods) and evaluate models to solve the RSVQA task. We report the results obtained by applying a model based on Convolutional Neural Networks (CNNs) for the visual part and on a Recurrent Neural Network (RNN) for the natural language part to this task. The model is trained on the two datasets, yielding promising results in both cases.

Diego Marcos, Sylvain Lobry, Devis Tuia

A main issue preventing the use of Convolutional Neural Networks (CNN) in end user applications is the low level of transparency in the decision process. Previous work on CNN interpretability has mostly focused either on localizing the regions of the image that contribute to the result or on building an external model that generates plausible explanations. However, the former does not provide any semantic information and the latter does not guarantee the faithfulness of the explanation. We propose an intermediate representation composed of multiple Semantically Interpretable Activation Maps (SIAM) indicating the presence of predefined attributes at different locations of the image. These attribute maps are then linearly combined to produce the final output. This gives the user insight into what the model has seen, where, and a final output directly linked to this information in a comprehensive and interpretable way. We test the method on the task of landscape scenicness (aesthetic value) estimation, using an intermediate representation of 33 attributes from the SUN Attributes database. The results confirm that SIAM makes it possible to understand what attributes in the image are contributing to the final score and where they are located. Since it is based on learning from multiple tasks and datasets, SIAM improve the explanability of the prediction without additional annotation efforts or computational overhead at inference time, while keeping good performances on both the final and intermediate tasks.

Benjamin Kellenberger, Diego Marcos, Sylvain Lobry et al.

We present an Active Learning (AL) strategy for re-using a deep Convolutional Neural Network (CNN)-based object detector on a new dataset. This is of particular interest for wildlife conservation: given a set of images acquired with an Unmanned Aerial Vehicle (UAV) and manually labeled gound truth, our goal is to train an animal detector that can be re-used for repeated acquisitions, e.g. in follow-up years. Domain shifts between datasets typically prevent such a direct model application. We thus propose to bridge this gap using AL and introduce a new criterion called Transfer Sampling (TS). TS uses Optimal Transport to find corresponding regions between the source and the target datasets in the space of CNN activations. The CNN scores in the source dataset are used to rank the samples according to their likelihood of being animals, and this ranking is transferred to the target dataset. Unlike conventional AL criteria that exploit model uncertainty, TS focuses on very confident samples, thus allowing a quick retrieval of true positives in the target dataset, where positives are typically extremely rare and difficult to find by visual inspection. We extend TS with a new window cropping strategy that further accelerates sample retrieval. Our experiments show that with both strategies combined, less than half a percent of oracle-provided labels are enough to find almost 80% of the animals in challenging sets of UAV images, beating all baselines by a margin.

Kilian Fatras, Bharath Bhushan Damodaran, Sylvain Lobry et al.

Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this goal, we propose a new adversarial regularization scheme based on the Wasserstein distance. Using this distance allows taking into account specific relations between classes by leveraging the geometric properties of the labels space. Our Wasserstein Adversarial Regularization (WAR) encodes a selective regularization, which promotes smoothness of the classifier between some classes, while preserving sufficient complexity of the decision boundary between others. We first discuss how and why adversarial regularization can be used in the context of label noise and then show the effectiveness of our method on five datasets corrupted with noisy labels: in both benchmarks and real datasets, WAR outperforms the state-of-the-art competitors.

John E. Vargas-Muñoz, Sylvain Lobry, Alexandre X. Falcão et al.

Rural building mapping is paramount to support demographic studies and plan actions in response to crisis that affect those areas. Rural building annotations exist in OpenStreetMap (OSM), but their quality and quantity are not sufficient for training models that can create accurate rural building maps. The problems with these annotations essentially fall into three categories: (i) most commonly, many annotations are geometrically misaligned with the updated imagery; (ii) some annotations do not correspond to buildings in the images (they are misannotations or the buildings have been destroyed); and (iii) some annotations are missing for buildings in the images (the buildings were never annotated or were built between subsequent image acquisitions). First, we propose a method based on Markov Random Field (MRF) to align the buildings with their annotations. The method maximizes the correlation between annotations and a building probability map while enforcing that nearby buildings have similar alignment vectors. Second, the annotations with no evidence in the building probability map are removed. Third, we present a method to detect non-annotated buildings with predefined shapes and add their annotation. The proposed methodology shows considerable improvement in accuracy of the OSM annotations for two regions of Tanzania and Zimbabwe, being more accurate than state-of-the-art baselines.

Diego Marcos, Benjamin Kellenberger, Sylvain Lobry et al.

We study the effect of injecting local scale equivariance into Convolutional Neural Networks. This is done by applying each convolutional filter at multiple scales. The output is a vector field encoding for the maximally activating scale and the scale itself, which is further processed by the following convolutional layers. This allows all the intermediate representations to be locally scale equivariant. We show that this improves the performance of the model by over $20\%$ in the scale equivariant task of regressing the scaling factor applied to randomly scaled MNIST digits. Furthermore, we find it also useful for scale invariant tasks, such as the actual classification of randomly scaled digits. This highlights the usefulness of allowing for a compact representation that can also learn relationships between different local scales by keeping internal scale equivariance.