arXiv subjects

Roberto Interdonato

Publications and source records attributed to Roberto Interdonato.

At least 19 recordsLinked to original sources

arXiv2026

Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification

Multi-modal classification leverages complementary information across diverse data sources to enhance predictive performance. However, real-world scenarios subject to operational constraints, such as sensor failures or privacy restrictions, lead to inconsistent modality availability between training and inference times. To handle missing modalities, prior studies have mainly covered bimodal data setups and focused on designing robust fusion processes. Instead, we adopt a multi-modal co-learning framework that prioritizes inter-modal collaboration rather than multi-modal fusion. Specifically, we consider that any subset of modalities may be absent, without assuming predefined missing-modality patterns, an inference scenario we refer to as missing arbitrary modalities. To address this challenge, we introduce two alternative approaches that leverage information at both feature- and decision-level. Experiments on two multi-modal classification benchmarks demonstrate significant robustness gains in various missing modality conditions. The first method shows more robust behavior under minimal missing conditions, where a single modality is absent, whereas the second performs better under extreme missing conditions, where all-but-one modalities are missing. Our code is available at https://github.com/fmenat/Co4Miss.

cs.CV↗

arXiv2025

Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration

Multi-modal co-learning is emerging as an effective paradigm in machine learning, enabling models to collaboratively learn from different modalities to enhance single-modality predictions. Earth Observation (EO) represents a quintessential domain for multi-modal data analysis, wherein diverse remote sensors collect data to sense our planet. This unprecedented volume of data introduces novel challenges. Specifically, the access to the same sensor modalities at both training and inference stages becomes increasingly complex based on real-world constraints affecting remote sensing platforms. In this context, multi-modal co-learning presents a promising strategy to leverage the vast amount of sensor-derived data available at the training stage to improve single-modality models for inference-time deployment. Most current research efforts focus on designing customized solutions for either particular downstream tasks or specific modalities available at the inference stage. To address this, we propose a novel multi-modal co-learning framework capable of generalizing across various tasks without targeting a specific modality for inference. Our approach combines contrastive and modality discriminative learning together to guide single-modality models to structure the internal model manifold into modality-shared and modality-specific information. We evaluate our framework on four EO benchmarks spanning classification and regression tasks across different sensor modalities, where only one of the modalities available during training is accessible at inference time. Our results demonstrate consistent predictive improvements over state-of-the-art approaches from the recent machine learning and computer vision literature, as well as EO-specific methods. The obtained findings validate our framework in the single-modality inference scenarios across a diverse range of EO applications.

cs.CV↗

arXiv2025

TimeSenCLIP: A Time Series Vision-Language Model for Remote Sensing

Vision-language models (VLMs) have shown significant promise in remote sensing applications, particularly for land-use and land-cover (LULC) mapping via zero-shot classification and retrieval. However, current approaches face several key challenges, such as the dependence on caption-based supervision, which is often not available or very limited in terms of the covered semantics, and the fact of being adapted from generic VLM architectures that are suitable for very high resolution images. Consequently, these models tend to prioritize spatial context over spectral and temporal information, limiting their effectiveness for medium-resolution remote sensing imagery. In this work, we present TimeSenCLIP, a lightweight VLM for remote sensing time series, using a cross-view temporal contrastive framework to align multispectral Sentinel-2 time series with geo-tagged ground-level imagery, without requiring textual annotations. Unlike prior VLMs, TimeSenCLIP emphasizes temporal and spectral signals over spatial context, investigating whether single-pixel time series contain sufficient information for solving a variety of tasks.

cs.CV↗

arXiv2025

Atomizer: Generalizing to new modalities by breaking satellite images down to a set of scalars

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.

cs.CV↗

arXiv2024

Adaptations of AI models for querying the LandMatrix database in natural language

The Land Matrix initiative (https://landmatrix.org) and its global observatory aim to provide reliable data on large-scale land acquisitions to inform debates and actions in sectors such as agriculture, extraction, or energy in low- and middle-income countries. Although these data are recognized in the academic world, they remain underutilized in public policy, mainly due to the complexity of access and exploitation, which requires technical expertise and a good understanding of the database schema. The objective of this work is to simplify access to data from different database systems. The methods proposed in this article are evaluated using data from the Land Matrix. This work presents various comparisons of Large Language Models (LLMs) as well as combinations of LLM adaptations (Prompt Engineering, RAG, Agents) to query different database systems (GraphQL and REST queries). The experiments are reproducible, and a demonstration is available online: https://github.com/tetis-nlp/landmatrix-graphql-python.

cs.CL↗

arXiv2024

Agro-STAY : Collecte de donn\'ees et analyse des informations en agriculture alternative issues de YouTube

To address the current crises (climatic, social, economic), the self-sufficiency -- a set of practices that combine energy sobriety, self-production of food and energy, and self-construction - arouses an increasing interest. The CNRS STAY project (Savoirs Techniques pour l'Auto-suffisance, sur YouTube) explores this topic by analyzing techniques shared on YouTube. We present Agro-STAY, a platform designed for the collection, processing, and visualization of data from YouTube videos and their comments. We use Natural Language Processing (NLP) techniques and language models, which enable a fine-grained analysis of alternative agricultural practice described online. -- Face aux crises actuelles (climatiques, sociales, \'economiques), l'auto-suffisance -- ensemble de pratiques combinant sobri\'et\'e \'energ\'etique, autoproduction alimentaire et \'energ\'etique et autoconstruction - suscite un int\'er\^et croissant. Le projet CNRS STAY (Savoirs Techniques pour l'Auto-suffisance, sur YouTube) s'inscrit dans ce domaine en analysant les savoirs techniques diffus\'es sur YouTube. Nous pr\'esentons Agro-STAY, une plateforme d\'edi\'ee \`a la collecte, au traitement et \`a la visualisation de donn\'ees issues de vid\'eos YouTube et de leurs commentaires. En mobilisant des techniques de traitement automatique des langues (TAL) et des mod\`eles de langues, ce travail permet une analyse fine des pratiques agricoles alternatives d\'ecrites en ligne.

cs.IR↗

arXiv2024

SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting

Pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive zero-shot classification capabilities with free-form prompts and even show some generalization in specialized domains. However, their performance on satellite imagery is limited due to the underrepresentation of such data in their training sets, which predominantly consist of ground-level images. Existing prompting techniques for satellite imagery are often restricted to generic phrases like a satellite image of ..., limiting their effectiveness for zero-shot land-use and land-cover (LULC) mapping. To address these challenges, we introduce SenCLIP, which transfers CLIPs representation to Sentinel-2 imagery by leveraging a large dataset of Sentinel-2 images paired with geotagged ground-level photos from across Europe. We evaluate SenCLIP alongside other SOTA remote sensing VLMs on zero-shot LULC mapping tasks using the EuroSAT and BigEarthNet datasets with both aerial and ground-level prompting styles. Our approach, which aligns ground-level representations with satellite imagery, demonstrates significant improvements in classification accuracy across both prompt styles, opening new possibilities for applying free-form textual descriptions in zero-shot LULC mapping.

cs.CV↗

arXiv2024

Evaluation of Geographical Distortions in Language Models

Language models now constitute essential tools for improving efficiency for many professional tasks such as writing, coding, or learning. For this reason, it is imperative to identify inherent biases. In the field of Natural Language Processing, five sources of bias are well-identified: data, annotation, representation, models, and research design. This study focuses on biases related to geographical knowledge. We explore the connection between geography and language models by highlighting their tendency to misrepresent spatial information, thus leading to distortions in the representation of geographical distances. This study introduces four indicators to assess these distortions, by comparing geographical and semantic distances. Experiments are conducted from these four indicators with ten widely used language models. Results underscore the critical necessity of inspecting and rectifying spatial biases in language models to ensure accurate and equitable representations.

cs.CL↗

arXiv2023

An evaluation framework for comparing epidemic intelligence systems

In the context of Epidemic Intelligence, many Event-Based Surveillance (EBS) systems have been proposed in the literature to promote the early identification and characterization of potential health threats from online sources of any nature. Each EBS system has its own surveillance definitions and priorities, therefore this makes the task of selecting the most appropriate EBS system for a given situation a challenge for end-users. In this work, we propose a new evaluation framework to address this issue. It first transforms the raw input epidemiological event data into a set of normalized events with multi-granularity, then conducts a descriptive retrospective analysis based on four evaluation objectives: spatial, temporal, thematic and source analysis. We illustrate its relevance by applying it to an Avian Influenza dataset collected by a selection of EBS systems, and show how our framework allows identifying their strengths and drawbacks in terms of epidemic surveillance.

cs.IR↗

arXiv2021

Community Detection in Multiplex Networks

A multiplex network models different modes of interaction among same-type entities. In this article we provide a taxonomy of community detection algorithms in multiplex networks. We characterize the different algorithms based on various properties and we discuss the type of communities detected by each method. We then provide an extensive experimental evaluation of the reviewed methods to answer three main questions: to what extent the evaluated methods are able to detect ground-truth communities, to what extent different methods produce similar community structures and to what extent the evaluated methods are scalable. One goal of this survey is to help scholars and practitioners to choose the right methods for the data and the task at hand, while also emphasizing when such choice is problematic.

cs.SI↗

arXiv2020

Attentive Weakly Supervised land cover mapping for object-based satellite image time series data with spatial interpretation

Nowadays, modern Earth Observation systems continuously collect massive amounts of satellite information. The unprecedented possibility to acquire high resolution Satellite Image Time Series (SITS) data (series of images with high revisit time period on the same geographical area) is opening new opportunities to monitor the different aspects of the Earth Surface but, at the same time, it is raising up new challenges in term of suitable methods to analyze and exploit such huge amount of rich and complex image data. One of the main task associated to SITS data analysis is related to land cover mapping where satellite data are exploited via learning methods to recover the Earth Surface status aka the corresponding land cover classes. Due to operational constraints, the collected label information, on which machine learning strategies are trained, is often limited in volume and obtained at coarse granularity carrying out inexact and weak knowledge that can affect the whole process. To cope with such issues, in the context of object-based SITS land cover mapping, we propose a new deep learning framework, named TASSEL (aTtentive weAkly Supervised Satellite image time sEries cLassifier), that is able to intelligently exploit the weak supervision provided by the coarse granularity labels. Furthermore, our framework also produces an additional side-information that supports the model interpretability with the aim to make the black box gray. Such side-information allows to associate spatial interpretation to the model decision via visual inspection.

cs.CV↗

arXiv2020

Multilayer network simplification: approaches, models and methods

Multilayer networks have been widely used to represent and analyze systems of interconnected entities where both the entities and their connections can be of different types. However, real multilayer networks can be difficult to analyze because of irrelevant information, such as layers not related to the objective of the analysis, because of their size, or because traditional methods defined to analyze simple networks do not have a straightforward extension able to handle multiple layers. Therefore, a number of methods have been devised in the literature to simplify multilayer networks with the objective of improving our ability to analyze them. In this article we provide a unified and practical taxonomy of existing simplification approaches, and we identify categories of multilayer network simplification methods that are still underdeveloped, as well as emerging trends.

cs.SI↗

arXiv2020

Fine grained classification for multi-source land cover mapping

Nowadays, there is a general agreement on the need to better characterize agricultural monitoring systems in response to the global changes. Timely and accurate land use/land cover mapping can support this vision by providing useful information at fine scale. Here, a deep learning approach is proposed to deal with multi-source land cover mapping at object level. The approach is based on an extension of Recurrent Neural Network enriched via an attention mechanism dedicated to multi-temporal data context. Moreover, a new hierarchical pretraining strategy designed to exploit specific domain knowledge available under hierarchical relationships within land cover classes is introduced. Experiments carried out on the Reunion island - a french overseas department - demonstrate the significance of the proposal compared to remote sensing standard approaches for land cover mapping.

cs.CV↗

arXiv2019

Object-based multi-temporal and multi-source land cover mapping leveraging hierarchical class relationships

European satellite missions Sentinel-1 (S1) and Sentinel-2 (S2) provide at highspatial resolution and high revisit time, respectively, radar and optical imagesthat support a wide range of Earth surface monitoring tasks such as LandUse/Land Cover mapping. A long-standing challenge in the remote sensingcommunity is about how to efficiently exploit multiple sources of information and leverage their complementary. In this particular case, get the most out ofradar and optical satellite image time series (SITS). Here, we propose to dealwith land cover mapping through a deep learning framework especially tailoredto leverage the multi-source complementarity provided by radar and opticalSITS. The proposed architecture is based on an extension of Recurrent NeuralNetwork (RNN) enriched via a customized attention mechanism capable to fitthe specificity of SITS data. In addition, we propose a new pretraining strategythat exploits domain expert knowledge to guide the model parameter initial-ization. Thorough experimental evaluations involving several machine learningcompetitors, on two contrasted study sites, have demonstrated the suitabilityof our new attention mechanism combined with the extend RNN model as wellas the benefit/limit to inject domain expert knowledge in the neural networktraining process.

cs.LG↗

arXiv2019

Supervised level-wise pretraining for recurrent neural network initialization in multi-class classification

Recurrent Neural Networks (RNNs) can be seriously impacted by the initial parameters assignment, which may result in poor generalization performances on new unseen data. With the objective to tackle this crucial issue, in the context of RNN based classification, we propose a new supervised layer-wise pretraining strategy to initialize network parameters. The proposed approach leverages a data-aware strategy that sets up a taxonomy of classification problems automatically derived by the model behavior. To the best of our knowledge, despite the great interest in RNN-based classification, this is the first data-aware strategy dealing with the initialization of such models. The proposed strategy has been tested on four benchmarks coming from two different domains, i.e., Speech Recognition and Remote Sensing. Results underline the significance of our approach and point out that data-aware strategies positively support the initialization of Recurrent Neural Network based classification models.

cs.LG↗

arXiv2018

Combining Sentinel-1 and Sentinel-2 Time Series via RNN for object-based land cover classification

Radar and Optical Satellite Image Time Series (SITS) are sources of information that are commonly employed to monitor earth surfaces for tasks related to ecology, agriculture, mobility, land management planning and land cover monitoring. Many studies have been conducted using one of the two sources, but how to smartly combine the complementary information provided by radar and optical SITS is still an open challenge. In this context, we propose a new neural architecture for the combination of Sentinel-1 (S1) and Sentinel-2 (S2) imagery at object level, applied to a real-world land cover classification task. Experiments carried out on the Reunion Island, a overseas department of France in the Indian Ocean, demonstrate the significance of our proposal.

cs.CV↗

arXiv2018

DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn

Nowadays, modern Earth Observation systems continuously generate huge amounts of data. A notable example is represented by the Sentinel-2 mission, which provides images at high spatial resolution (up to 10m) with high temporal revisit period (every 5 days), which can be organized in Satellite Image Time Series (SITS). While the use of SITS has been proved to be beneficial in the context of Land Use/Land Cover (LULC) map generation, unfortunately, machine learning approaches commonly leveraged in remote sensing field fail to take advantage of spatio-temporal dependencies present in such data. Recently, new generation deep learning methods allowed to significantly advance research in this field. These approaches have generally focused on a single type of neural network, i.e., Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), which model different but complementary information: spatial autocorrelation (CNNs) and temporal dependencies (RNNs). In this work, we propose the first deep learning architecture for the analysis of SITS data, namely \method{} (DUal view Point deep Learning architecture for time series classificatiOn), that combines Convolutional and Recurrent neural networks to exploit their complementarity. Our hypothesis is that, since CNNs and RNNs capture different aspects of the data, a combination of both models would produce a more diverse and complete representation of the information for the underlying land cover classification task. Experiments carried out on two study sites characterized by different land cover characteristics (i.e., the \textit{Gard} site in France and the \textit{Reunion Island} in the Indian Ocean), demonstrate the significance of our proposal.

cs.CV↗

arXiv2018

Topology-driven Diversity for Targeted Influence Maximization with Application to User Engagement in Social Networks

Research on influence maximization has often to cope with marketing needs relating to the propagation of information towards specific users. However, little attention has been paid to the fact that the success of an information diffusion campaign might depend not only on the number of the initial influencers to be detected but also on their diversity w.r.t. the target of the campaign. Our main hypothesis is that if we learn seeds that are not only capable of influencing but also are linked to more diverse (groups of) users, then the influence triggers will be diversified as well, and hence the target users will get higher chance of being engaged. Upon this intuition, we define a novel problem, named Diversity-sensitive Targeted Influence Maximization (DTIM), which assumes to model user diversity by exploiting only topological information within a social graph. To the best of our knowledge, we are the first to bring the concept of topology-driven diversity into targeted IM problems, for which we define two alternative definitions. Accordingly, we propose approximate solutions of DTIM, which detect a size-k set of users that maximizes the diversity-sensitive capital objective function, for a given selection of target users. We evaluate our DTIM methods on a special case of user engagement in online social networks, which concerns users who are not actively involved in the community life. Experimental evaluation on real networks has demonstrated the meaningfulness of our approach, also highlighting the opportunity of further development of solutions for DTIM applications.

cs.SI↗