Search Results for author: Andrea Prati

Found 29 papers, 17 papers with code

Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensing

2 code implementations29 Apr 2024 Leonardo Rossi, Vittorio Bernuzzi, Tomaso Fontanini, Massimo Bertozzi, Andrea Prati

Due to the limitations of current optical and sensor technologies and the high cost of updating them, the spectral and spatial resolution of satellites may not always meet desired requirements.

Multispectral Image Super-resolution Semantic Segmentation +1

Self-Balanced R-CNN for Instance Segmentation

1 code implementation25 Apr 2024 Leonardo Rossi, Akbar Karimi, Andrea Prati

Current state-of-the-art two-stage models on instance segmentation task suffer from several types of imbalances.

Instance Segmentation object-detection +2

Adversarial Identity Injection for Semantic Face Image Synthesis

no code implementations16 Apr 2024 Giuseppe Tarollo, Tomaso Fontanini, Claudio Ferrari, Guido Borghi, Andrea Prati

Among all the explored techniques, Semantic Image Synthesis (SIS) methods, whose goal is to generate an image conditioned on a semantic segmentation mask, are the most promising, even though preserving the perceived identity of the input subject is not their main concern.

Adversarial Attack Face Generation +2

Towards Controllable Face Generation with Semantic Latent Diffusion Models

1 code implementation19 Mar 2024 Alex Ergasti, Claudio Ferrari, Tomaso Fontanini, Massimo Bertozzi, Andrea Prati

To address that, in this paper we propose a SIS framework based on a novel Latent Diffusion Model architecture for human face generation and editing that is both able to reproduce and manipulate a real reference image and generate diversity-driven results.

Diversity Face Generation

Semantic Image Synthesis via Class-Adaptive Cross-Attention

2 code implementations30 Aug 2023 Tomaso Fontanini, Claudio Ferrari, Giuseppe Lisanti, Massimo Bertozzi, Andrea Prati

Thus, they tend to overlook global image statistics, ultimately leading to unconvincing local style editing and causing global inconsistencies such as color or illumination distribution shifts.

Image Generation Semantic Segmentation +1

Automatic Generation of Semantic Parts for Face Image Synthesis

1 code implementation11 Jul 2023 Tomaso Fontanini, Claudio Ferrari, Massimo Bertozzi, Andrea Prati

Also, we show our model can be put before a SIS generator, opening the way to a fully automatic generation control of both shape and texture.

Decoder Image Generation +2

LDD: A Dataset for Grape Diseases Object Detection and Instance Segmentation

no code implementations21 Jun 2022 Leonardo Rossi, Marco Valenti, Sara Elisabetta Legler, Andrea Prati

The Instance Segmentation task, an extension of the well-known Object Detection task, is of great help in many areas, such as precision agriculture: being able to automatically identify plant organs and the possible diseases associated with them, allows to effectively scale and automate crop monitoring and its diseases control.

Instance Segmentation Object +4

Improving Localization for Semi-Supervised Object Detection

1 code implementation21 Jun 2022 Leonardo Rossi, Akbar Karimi, Andrea Prati

Nowadays, Semi-Supervised Object Detection (SSOD) is a hot topic, since, while it is rather easy to collect images for creating a new dataset, labeling them is still an expensive and time-consuming task.

Object object-detection +3

AEDA: An Easier Data Augmentation Technique for Text Classification

2 code implementations Findings (EMNLP) 2021 Akbar Karimi, Leonardo Rossi, Andrea Prati

This is an easier technique to implement for data augmentation than EDA method (Wei and Zou, 2019) with which we compare our results.

Data Augmentation Sentence +2

Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing

1 code implementation3 Apr 2021 Leonardo Rossi, Akbar Karimi, Andrea Prati

Within the field of instance segmentation, most of the state-of-the-art deep learning networks rely nowadays on cascade architectures, where multiple object detectors are trained sequentially, re-sampling the ground truth at each step.

Instance Segmentation Object Detection +1

UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model

1 code implementation SEMEVAL 2021 Akbar Karimi, Leonardo Rossi, Andrea Prati

We tackle this problem utilizing a combination of a state-of-the-art pre-trained language model (CharacterBERT) and a traditional bag-of-words technique.

Language Modelling Toxic Spans Detection

A novel Region of Interest Extraction Layer for Instance Segmentation

5 code implementations28 Apr 2020 Leonardo Rossi, Akbar Karimi, Andrea Prati

Given the wide diffusion of deep neural network architectures for computer vision tasks, several new applications are nowadays more and more feasible.

Instance Segmentation object-detection +3

Adversarial Training for Aspect-Based Sentiment Analysis with BERT

4 code implementations30 Jan 2020 Akbar Karimi, Leonardo Rossi, Andrea Prati

In this work, we apply adversarial training, which was put forward by Goodfellow et al. (2014), to the post-trained BERT (BERT-PT) language model proposed by Xu et al. (2019) on the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis.

Aspect-Based Sentiment Analysis Aspect Extraction +2

MetalGAN: Multi-Domain Label-Less Image Synthesis Using cGANs and Meta-Learning

no code implementations5 Dec 2019 Tomaso Fontanini, Eleonora Iotti, Luca Donati, Andrea Prati

Above all, producing images belonging to different domains by using a single architecture is a very relevant goal for image generation.

Attribute Generative Adversarial Network +2

MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization

no code implementations17 Sep 2019 Tomaso Fontanini, Eleonora Iotti, Andrea Prati

In recent years, the majority of works on deep-learning-based image colorization have focused on how to make a good use of the enormous datasets currently available.

Colorization Image Colorization +1

Genetic Algorithms for the Optimization of Diffusion Parameters in Content-Based Image Retrieval

no code implementations19 Aug 2019 Federico Magliani, Laura Sani, Stefano Cagnoni, Andrea Prati

We propose to use genetic algorithms to find the optimal setting of all the diffusion parameters with respect to retrieval performance for each different dataset.

Content-Based Image Retrieval Retrieval

An Efficient Approximate kNN Graph Method for Diffusion on Image Retrieval

1 code implementation18 Apr 2019 Federico Magliani, Kevin McGuinness, Eva Mohedano, Andrea Prati

The application of the diffusion in many computer vision and artificial intelligence projects has been shown to give excellent improvements in performance.

Image Retrieval Retrieval

An accurate retrieval through R-MAC+ descriptors for landmark recognition

1 code implementation22 Jun 2018 Federico Magliani, Andrea Prati

The landmark recognition problem is far from being solved, but with the use of features extracted from intermediate layers of Convolutional Neural Networks (CNNs), excellent results have been obtained.

Landmark Recognition Retrieval

Efficient Nearest Neighbors Search for Large-Scale Landmark Recognition

1 code implementation15 Jun 2018 Federico Magliani, Tomaso Fontanini, Andrea Prati

It allows to drastically reduce the query time and outperforms the accuracy results compared to the state-of-the-art methods for large-scale landmark recognition.

Landmark Recognition Retrieval

A complete hand-drawn sketch vectorization framework

no code implementations16 Feb 2018 Luca Donati, Simone Cesano, Andrea Prati

Vectorizing hand-drawn sketches is a challenging task, which is of paramount importance for creating CAD vectorized versions for the fashion and creative workflows.

Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets

no code implementations19 Jun 2017 Yonatan Tariku Tesfaye, Eyasu Zemene, Andrea Prati, Marcello Pelillo, Mubarak Shah

In this paper, a unified three-layer hierarchical approach for solving tracking problems in multiple non-overlapping cameras is proposed.

Clustering

A location-aware embedding technique for accurate landmark recognition

no code implementations19 Apr 2017 Federico Magliani, Navid Mahmoudian Bidgoli, Andrea Prati

The current state of the research in landmark recognition highlights the good accuracy which can be achieved by embedding techniques, such as Fisher vector and VLAD.

Landmark Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.