no code implementations • 17 Apr 2024 • Cassio F. Dantas, Raffaele Gaetano, Claudia Paris, Dino Ienco
Typically, when creating a land cover (LC) map, precise ground truth data is collected through time-consuming and expensive field campaigns.
no code implementations • 27 Feb 2024 • Alexandre Defossez, Samuel Alleaume, Marc Montadert, Dino Ienco, Sandra Luque
Indeed, the extraction of variables from remote sensing helped to describe the area studied at appropriate spatial and temporal scales: horizontal and vertical structure (heterogeneity), functioning (vegetation indices), phenology (seasonal or inter-annual dynamics) and biodiversity.
no code implementations • 3 Oct 2023 • Konstantinos P. Panousis, Dino Ienco, Diego Marcos
Deep Learning algorithms have recently gained significant attention due to their impressive performance.
1 code implementation • ICCV 2023 • Robert van der Klis, Stephan Alaniz, Massimiliano Mancini, Cassio F. Dantas, Dino Ienco, Zeynep Akata, Diego Marcos
Fine-grained classification often requires recognizing specific object parts, such as beak shape and wing patterns for birds.
1 code implementation • 23 Aug 2023 • Ananthu Aniraj, Cassio F. Dantas, Dino Ienco, Diego Marcos
Models for fine-grained image classification tasks, where the difference between some classes can be extremely subtle and the number of samples per class tends to be low, are particularly prone to picking up background-related biases and demand robust methods to handle potential examples with out-of-distribution (OOD) backgrounds.
1 code implementation • 21 Aug 2023 • Konstantinos P. Panousis, Dino Ienco, Diego Marcos
The recent mass adoption of DNNs, even in safety-critical scenarios, has shifted the focus of the research community towards the creation of inherently intrepretable models.
no code implementations • 4 Jan 2023 • Cassio F. Dantas, Diego Marcos, Dino Ienco
Furthermore, plausibility/realism of the generated counterfactual explanations is enforced via the proposed adversarial learning strategy.
no code implementations • 30 Apr 2020 • Dino Ienco, Yawogan Jean Eudes Gbodjo, Roberto Interdonato, Raffaele Gaetano
Nowadays, modern Earth Observation systems continuously collect massive amounts of satellite information.
1 code implementation • 4 Apr 2020 • Yawogan Jean Eudes Gbodjo, Dino Ienco, Louise Leroux, Roberto Interdonato, Raffaelle Gaetano
Nowadays, there is a general agreement on the need to better characterize agricultural monitoring systems in response to the global changes.
1 code implementation • 20 Nov 2019 • Yawogan Jean Eudes Gbodjo, Dino Ienco, Louise Leroux, Roberto Interdonato, Raffaele Gaetano, Babacar Ndao, Stephane Dupuy
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.
no code implementations • 4 Nov 2019 • Dino Ienco, Roberto Interdonato, Raffaele Gaetano
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.
no code implementations • 13 Dec 2018 • Dino Ienco, Raffaele Gaetano, Roberto Interdonato Kenji Ose, Dinh Ho Tong Minh
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.
no code implementations • 20 Sep 2018 • Roberto Interdonato, Dino Ienco, Raffaele Gaetano, Kenji Ose
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.
no code implementations • 29 Jun 2018 • Raffaele Gaetano, Dino Ienco, Kenji Ose, Remi Cresson
Common techniques to produce land cover maps from such VHSR images typically opt for a prior pansharpening of the multi-resolution source for a full resolution processing.
no code implementations • 11 Aug 2017 • Dinh Ho Tong Minh, Dino Ienco, Raffaele Gaetano, Nathalie Lalande, Emile Ndikumana, Faycal Osman, Pierre Maurel
The objective of this paper is to provide a better understanding of the capabilities of radar Sentinel-1 and deep learning concerning about mapping winter vegetation quality coverage.
no code implementations • 13 Apr 2017 • Dino Ienco, Raffaele Gaetano, Claire Dupaquier, Pierre Maurel
Nowadays, modern earth observation programs produce huge volumes of satellite images time series (SITS) that can be useful to monitor geographical areas through time.
no code implementations • 16 Nov 2015 • Lionel Pibre, Pasquet Jérôme, Dino Ienco, Marc Chaumont
In this paper, we follow-up the study of Qian et al., and show that, due to intrinsic joint minimization, the results obtained from a Convolutional Neural Network (CNN) or a Fully Connected Neural Network (FNN), if well parameterized, surpass the conventional use of a RM with an EC.