no code implementations • 13 Mar 2024 • Alex Levering, Diego Marcos, Devis Tuia
In our research we test data and models for the recognition of housing quality in the city of Amsterdam from ground-level and aerial imagery.
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.
no code implementations • 1 Sep 2023 • Alex Levering, Diego Marcos, Devis Tuia
In this paper we explore deep learning models to monitor longitudinal liveability changes in Dutch cities at the neighbourhood level.
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 • 7 Aug 2023 • Christophe Botella, Benjamin Deneu, Diego Marcos, Maximilien Servajean, Joaquim Estopinan, Théo Larcher, César Leblanc, Pierre Bonnet, Alexis Joly
We designed a European scale dataset covering around ten thousand plant species to calibrate and evaluate SDM predictions of species composition in space and time at high spatial resolution (~ten meters), and their spatial transferability.
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.
1 code implementation • 27 Jul 2022 • Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos, Zeynep Akata
Toward equipping machines with such capabilities, we propose the Primitive-based Sketch Abstraction task where the goal is to represent sketches using a fixed set of drawing primitives under the influence of a budget.
no code implementations • 18 May 2022 • Dilli R. Paudel, Diego Marcos, Allard de Wit, Hendrik Boogaard, Ioannis N. Athanasiadis
We propose a deep learning framework that uses high resolution inputs and low resolution labels to produce crop yield forecasts for both spatial levels.
1 code implementation • 20 Jan 2021 • Marrit Leenstra, Diego Marcos, Francesca Bovolo, Devis Tuia
While annotated images for change detection using satellite imagery are scarce and costly to obtain, there is a wealth of unlabeled images being generated every day.
Ranked #5 on Change Detection on OSCD - 13ch (using extra training data)
1 code implementation • 10 Jan 2021 • Yuansheng Hua, Diego Marcos, Lichao Mou, Xiao Xiang Zhu, Devis Tuia
Training Convolutional Neural Networks (CNNs) for very high resolution images requires a large quantity of high-quality pixel-level annotations, which is extremely labor- and time-consuming to produce.
no code implementations • 7 Dec 2020 • Devis Tuia, Diego Marcos, Gustau Camps-Valls
Remote sensing image classification exploiting multiple sensors is a very challenging problem: data from different modalities are affected by spectral distortions and mis-alignments of all kinds, and this hampers re-using models built for one image to be used successfully in other scenes.
1 code implementation • 18 Sep 2020 • Diego Marcos, Ruth Fong, Sylvain Lobry, Remi Flamary, Nicolas Courty, Devis Tuia
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.
no code implementations • 16 Mar 2020 • Sylvain Lobry, Diego Marcos, Jesse Murray, Devis Tuia
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.
no code implementations • 18 Sep 2019 • Diego Marcos, Sylvain Lobry, Devis Tuia
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.
no code implementations • 17 Jul 2019 • Benjamin Kellenberger, Diego Marcos, Sylvain Lobry, Devis Tuia
We present an Active Learning (AL) strategy for re-using a deep Convolutional Neural Network (CNN)-based object detector on a new dataset.
no code implementations • CVPR 2021 • Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata
Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user.
no code implementations • 31 Jul 2018 • Diego Marcos, Benjamin Kellenberger, Sylvain Lobry, Devis Tuia
We study the effect of injecting local scale equivariance into Convolutional Neural Networks.
no code implementations • 29 Jun 2018 • Benjamin Kellenberger, Diego Marcos, Devis Tuia
In this paper, we study how to scale CNNs to large wildlife census tasks and present a number of recommendations to train a CNN on a large UAV dataset.
no code implementations • 16 Mar 2018 • Diego Marcos, Michele Volpi, Benjamin Kellenberger, Devis Tuia
In remote sensing images, the absolute orientation of objects is arbitrary.
2 code implementations • CVPR 2018 • Diego Marcos, Devis Tuia, Benjamin Kellenberger, Lisa Zhang, Min Bai, Renjie Liao, Raquel Urtasun
The world is covered with millions of buildings, and precisely knowing each instance's position and extents is vital to a multitude of applications.
3 code implementations • ICCV 2017 • Diego Marcos, Michele Volpi, Nikos Komodakis, Devis Tuia
In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image.
Ranked #8 on Multi-tissue Nucleus Segmentation on Kumar
Breast Tumour Classification Colorectal Gland Segmentation: +5
no code implementations • CVPR 2016 • Diego Marcos, Raffay Hamid, Devis Tuia
The growing availability of very high resolution (<1 m/pixel) satellite and aerial images has opened up unprecedented opportunities to monitor and analyze the evolution of land-cover and land-use across the world.
1 code implementation • 22 Apr 2016 • Diego Marcos, Michele Volpi, Devis Tuia
We present a method for learning discriminative filters using a shallow Convolutional Neural Network (CNN).