1 code implementation • Ital-IA 2023 • Nicola Landro, Gabriele Destro, Stefano Taverni, Ignazio Gallo
We propose an extraction pipeline that employs question-answering models to get insight from unstructured data, allowing fast and efficient information retrieval from different sources.
1 code implementation • ISPRS Journal of Photogrammetry and Remote Sensing 2022 • Ignazio Gallo, Luigi Ranghetti, Nicola Landro, Riccardo La Grassa, Mirco Boschetti
In this paper we present a Deep Neural Network-based approach capable of generating (i) a crop map of the current season at a specific point in time (“In season mapping” conventionally at the end of the current year), along with (ii) all intermediate maps during the season able to describe in near real-time the evolution of crop presence (“Dynamic-mapping” at the temporal granularity of satellite imagery revisiting, e. g., 5 days for Sentinel-2 data).
1 code implementation • Remote Sensing 2022 • Riccardo La Grassa, Ignazio Gallo, Cristina Re, Gabriele Cremonese, Nicola Landro, Claudio Pernechele, Emanuele Simioni, Mattia Gatti
In this paper, we combine these last two concepts into a single end-to-end model and introduce a new generative adversarial network solution that estimates the DTM at 4× resolution from a single monocular image, called SRDiNet (super-resolution depth image network).
Ranked #1 on Depth Estimation on Mars DTM Estimation
Generative Adversarial Network Monocular Depth Estimation +2
1 code implementation • Information 2022 • Nicola Landro, Ignazio Gallo, Riccardo La Grassa, Edoardo Federici
Text summarization aims to produce a short summary containing relevant parts from a given text.
Ranked #1 on Abstractive Text Summarization on MLSum-it
1 code implementation • Sustainability 2022 • Ignazio Gallo, Nicola Landro, Riccardo La Grassa, Andrea Turconi
Therefore, in this work, we present a personalized food recommendation scheme, mapping the ingredients to the most resource-friendly dishes on the planet and in particular, selecting recipes that contain ingredients that consume as little water as possible for their production.
1 code implementation • Algorithms 2021 • Nicola Landro, Ignazio Gallo, Riccardo La Grassa
Nowadays, the transfer learning technique can be successfully applied in the deep learning field through techniques that fine-tune the CNN’s starting point so it may learn over a huge dataset such as ImageNet and continue to learn on a fixed dataset to achieve better performance.
1 code implementation • CAIP: Computer Analysis of Images and Patterns 2021 • Riccardo La Grassa, Ignazio Gallo, Nicola Landro
Fine-Grained classification models can expressly focus on the relevant details useful to distinguish highly similar classes typically when the intra-class variance is high and the inter-class variance is low given a dataset.
Ranked #1 on Fine-Grained Image Classification on FGVC-Aircraft
1 code implementation • CAIP: Computer Analysis of Images and Patterns 2021 • Riccardo La Grassa, Ignazio Gallo, Nicola Landro
We aim to reduce variances considering many centers per class, using the information from the hidden layers of a deep model, and decreasing the high response from the unnecessary areas of images detected along the baselines.
1 code implementation • isprs: International Journal of Geo-information 2021 • Ignazio Gallo, Riccardo La Grassa, Nicola Landro, Mirco Boschetti
In this paper, we provide an innovative contribution in the research domain dedicated to crop mapping by exploiting the of Sentinel-2 satellite images time series, with the specific aim to extract information on “where and when” crops are grown.
2 code implementations • Algorithsm MDPI 2021 • Nicola Landro, Ignazio Gallo, Riccardo La Grassa
In our article, we propose the use of the combination of two very different optimizers that, when used simultaneously, can exceed the performance of the single optimizers in very different problems.
1 code implementation • 25 Feb 2021 • Ignazio Gallo, Shah Nawaz, Nicola Landro, Riccardo La Grassa
The question we answer with this paper is: ‘can we convert a text document into an image to take advantage of image neural models to classify text documents?’ To answer this question we present a novel text classification method that converts a document into an encoded image, using word embedding.
1 code implementation • 17 Dec 2020 • Ignazio Gallo, Gabriele Magistrali, Nicola Landro, Riccardo La Grassa
Neural Architecture Search (NAS) has achieved remarkable results in deep learning applications in the past few years.
1 code implementation • 17 Dec 2020 • Ignazio Gallo, Gianmarco Ria, Nicola Landro, and Riccardo La Grassa
The modern digital world is becoming more and more multimodal.
Ranked #1 on Document Text Classification on Food-101
1 code implementation • 16 Nov 2020 • Nicola Landro, Ignazio Gallo, Riccardo La Grassa
Optimization methods (optimizers) get special attention for the efficient training of neural networks in the field of deep learning.
Ranked #1 on Stochastic Optimization on CIFAR-100
1 code implementation • 18 Sep 2020 • Riccardo La Grassa, Ignazio Gallo, Nicola Landro
In neural networks, the loss function represents the core of the learning process that leads the optimizer to an approximation of the optimal convergence error.
1 code implementation • 18 May 2020 • Riccardo La Grassa, Ignazio Gallo, Nicola Landro
A large amount of research on Convolutional Neural Networks has focused on flat Classification in the multi-class domain.
1 code implementation • 1 May 2020 • Nicola Landro, Ignazio Gallo, Riccardo La Grassa
Is it possible to improve the performance of a weak neural network using the knowledge acquired by a more powerful neural network?
no code implementations • 28 Apr 2020 • Muhammad Saad Saeed, Shah Nawaz, Pietro Morerio, Arif Mahmood, Ignazio Gallo, Muhammad Haroon Yousaf, Alessio Del Bue
Recent years have seen a surge in finding association between faces and voices within a cross-modal biometric application along with speaker recognition.
1 code implementation • 5 Apr 2020 • Riccardo La Grassa, Ignazio Gallo, Nicola Landro
A typical issue in Pattern Recognition is the non-uniformly sampled data, which modifies the general performance and capability of machine learning algorithms to make accurate predictions.
1 code implementation • 30 Mar 2020 • Riccardo La Grassa, Ignazio Gallo, Nicola Landro
We present a novel model called One Class Minimum Spanning Tree (OCmst) for novelty detection problem that uses a Convolutional Neural Network (CNN) as deep feature extractor and graph-based model based on Minimum Spanning Tree (MST).
3 code implementations • 16 Jan 2020 • Shah Nawaz, Alessandro Calefati, Moreno Caraffini, Nicola Landro, Ignazio Gallo
In recent years, natural language descriptions are used to obtain information on discriminative parts of the object.
Ranked #1 on Multi-Modal Document Classification on CUB-200-2011
no code implementations • 18 Sep 2019 • Shah Nawaz, Muhammad Kamran Janjua, Ignazio Gallo, Arif Mahmood, Alessandro Calefati
We quantitatively and qualitatively evaluate the proposed approach on VoxCeleb, a benchmarks audio-visual dataset on a multitude of tasks including cross-modal verification, cross-modal matching, and cross-modal retrieval.
no code implementations • 9 Sep 2019 • Riccardo La Grassa, Ignazio Gallo, Alessandro Calefati, Dimitri Ognibene
The objective is to select the best structures created during the training phase using an ensemble of spanning trees.
1 code implementation • 9 Sep 2019 • Ignazio Gallo, Shah Nawaz, Alessandro Calefati, Riccardo La Grassa, Nicola Landro
Visualization refers to our ability to create an image in our head based on the text we read or the words we hear.
no code implementations • 3 Sep 2019 • Shah Nawaz, Muhammad Kamran Janjua, Ignazio Gallo, Arif Mahmood, Alessandro Calefati, Faisal Shafait
Our proposed measure evaluates the semantic similarity between the image and text representations in the latent embedding space.
no code implementations • 14 Jun 2019 • Riccardo La Grassa, Ignazio Gallo, Alessandro Calefati, Dimitri Ognibene
One-class classifiers are trained with target class only samples.
1 code implementation • 2 Apr 2019 • Omer Arshad, Ignazio Gallo, Shah Nawaz, Alessandro Calefati
With massive explosion of social media such as Twitter and Instagram, people daily share billions of multimedia posts, containing images and text.
no code implementations • 16 Oct 2018 • Muhammad Kamran Janjua, Shah Nawaz, Alessandro Calefati, Ignazio Gallo
Majority of the current dimensionality reduction or retrieval techniques rely on embedding the learned feature representations onto a computable metric space.
1 code implementation • 3 Oct 2018 • Ignazio Gallo, Alessandro Calefati, Shah Nawaz, Muhammad Kamran Janjua
To learn feature representations of resulting images, standard Convolutional Neural Networks (CNNs) are employed for the classification task.
no code implementations • 31 Aug 2018 • Shah Nawaz, Alessandro Calefati, Muhammad Kamran Janjua, Ignazio Gallo
The question we answer with this work is: can we convert a text document into an image to exploit best image classification models to classify documents?
1 code implementation • 23 Jul 2018 • Alessandro Calefati, Muhammad Kamran Janjua, Shah Nawaz, Ignazio Gallo
Conventionally, CNNs have been trained with softmax as supervision signal to penalize the classification loss.
Ranked #8 on Face Verification on YouTube Faces DB
no code implementations • 19 Jul 2018 • Shah Nawaz, Muhammad Kamran Janjua, Alessandro Calefati, Ignazio Gallo
We show that text encodings can capture semantic relationships between multiple modalities.