Datasets and Publications

Despite recent advancements, Unsupervised Semantic Segmentation (USS) methods still exhibit a significant performance deficit compared to supervised approaches, particularly in binary semantic segmentation. This limitation arises because, without supervision, USS methods struggle to distinguish foreground from background image regions, particularly when the foreground contains small or uncommon objects. This issue is addressed by our proposed Extremely Weakly Supervised Binary Semantic Segmentation (EWS) framework. EWS expects minimal supervision, consisting only of a small set of one-pixel annotations explicitly belonging to the foreground class across the entire image dataset. Our approach leverages these one-pixel annotations and employs two contrastive losses to map visual transformer features into well-separated foreground and background feature clusters. Additionally, we propose a novel loss function to eliminate the need for hyperparameter tuning of the contrastive loss threshold, by dynamically computing it based on the similarity between the input image features. Even if we employ employ a single one-pixel annotation, EWS achieves competitive results in binary segmentation tasks while maintaining low computational costs, making it an efficient solution for critical segmentation applications.

The security and trustworthiness of participating DNN nodes are often overlooked during the design of modern Decentralized Deep Neural Networks (D-DNN). This paper introduces a shard-based distributed consensus protocol specifically tailored for DNN nodes operating over unreliable communication links. The proposed approach enhances D-DNN scalability, by enabling D-DNN systems having a large number of DNN nodes. This is achieved through a hierarchical consensus mechanism that partitions the D-DNN network into sub-networks (shards), leveraging Out-of-Distribution (OOD) detectors to localize and isolate the consensus process within each shard. Rather than randomly allocating DNN nodes into shards, the OOD detector can be employed to identify and group nodes with similar domain knowledge. This approach improves the overall D-DNN system robustness, by identifying and isolating malicious DNN nodes or once that have poor performance for a specific DNN task. Experimental results demonstrate improvements in the D-DNN system’s classification accuracy and reliability.

A typical way to label datasets for Deep Neural Network (DNN) training and testing is through crowdsourcing. However, there is no assurance that crowd workers will adhere to the data labeling criteria, refrain from introducing personal bias, or from spamming random labels. In order to address this issue, we propose a graph-based technique to assess annotator trustworthiness and adjust their involvement in the labeling process. Our proposed method not only improves data labels accuracy, by considering the agreement between annotators and ranking them based on their labeling trustworthiness, but also aims to enhance DNN inference performance by providing more accurate training data labels. We examine the constraints of conventional multi-annotation label aggregation techniques and compare them to our approach. Lastly, we demonstrate that our proposed method remains robust to artificially injected noisy annotations, surpassing the performance of previous state-of the-art work. The effectiveness of the proposed method is validated on an intrinsically subjective task, namely text sentiment analysis. 

In many real world applications (natural disaster management, urban development, infrastructure inspection) Unmanned Aerial Vehicles (UAVs) perform flights on different times, for scene image acquisition. Visual Place Recognition (VPR) methods can match newly acquired images with older ones, when the new and/or the old ones are not georeferenced. Most VPR solutions are based on image retrieval, where a query image scene is visually compared with that of many related images in a database, and the most relevant ones are retrieved. Deep learning-based VPR performance relies a lot on image dataset acquisition conditions, e.g. structured/unstructured scene visualization, single/multi-view image acquisition, illumination variations, or on-road/aerial view. Most of VPR methods are trained and tested on on-road views. This paper addresses the issue of image retrieval performance when large image databases are employed. To this end, we perform a comparison of some state of the art VPR methods on UAV image datasets, where the amount of database images is scaled, examine how well they generalize, and expand on some dataset creation gaps for this task.

In the realm of Natural Disaster Management (NDM), timely communication with local authorities is paramount for an effective response. To achieve this, multi-agent systems play a pivotal role by proficiently identifying and categorizing various disasters. In the field of Distributed Deep Neural Network (D-DNN) inference, such approaches often require DNN nodes to transmit their results to the cloud for inference, or they necessitate the establishment of a fixed topology network to enable inference directly on the edge, a practice prone to security risks. In this work, we propose a decentralized inference strategy tailored for fire classification tasks. In this approach, individual DNN nodes communicate within a network and enhance their predictions by considering other DNN node inference outputs that contribute to improving their individual performance. The overall coordination of the system on a specific decision is achieved through a consensus protocol, which acts as a universally accepted inference rule adopted by all DNN nodes operating within the system. We present a comprehensive experimental analysis, of the forestfire classification task, focusing on enhancing both individual DNN node performance and the stability of the consensus protocol.

This contribution aims to recommend a fully-fledged privacy-assessment applicable to future uses of Autonomous Systems (AS) for Natural Disaster Management (NDM) purposes. It claims that certain implementations may interfere with the right to privacy and the protection of personal data and analyses challenges stemming from (non-) compliance with the General Data Protection Regulation (GDPR). Moreover, it subjects the use of autonomous systems to the European Court of Human Rights’ (ECtHR) Legality – Legitimacy – Necessity testing (LLN-check). On this basis, it proposes a targeted and ex ante privacy-assessment to address legal uncertainty, resulting from the GDPR’s tech-neutrality and case law’s ex post (after the harm) adjudication. The recommended scheme, ideally involving experts from various disciplines who would moreover be independent, could apply before the actual use of any AS and give a ‘proceed’, a ‘proceed with conditions’ or a ‘do not proceed’ decision.

For civil protection purposes, risk is the probability of a calamitous event occurring that may cause harmful effects on the population, residential and productive settlements and infrastructure, within a particular area, in a given period of time. The work was carried out with the aim of being able to establish the municipal fire danger and risk index (IR), which define, respectively, the degree of danger and fire risk calculated on a regional basis and referred to the individual municipal territory, exploiting the typical functions of GIS tools and the new steps forward made by the application of artificial intelligence; however, the horizon to be reached is to be able to transform the algorithms into automated processes that can be used in platforms capable of returning outputs to end users.

EDGEmergency is a platform designed for disaster management that can dynamically leverage the edge infrastructure potentially already present within the emergency perimeter. Edge devices, from IoT to smartphones, possess an increasingly significant computational capacity that can be exploited, by changing their behavior in real-time and creating a pervasive local environment, capable of adapting perfectly to the specific context of reference. EDGEmergency, in fact, allows the creation of a unified computation environment leveraging the Cloud-Edge-Client Continuum concept, through which a computation cluster with zero configurations is created on-the-fly. The platform thus allows the deployment of distributed microservices on existing edge devices, installed by default for other purposes, through a modular and incremental logic that has the role of adapting best to the needs of the individual emergency, through advanced tools for analysis and monitoring, using artificial intelligence.

Natural disasters are more and more often present in our daily life. Many are the cases where these events affect people and economies. In this context, there is the need for a technological intervention in support of first responders, with solutions capable of make decisions on the disaster areas. Indeed, considering these scenarios are time-sensitive, the intention is moving the computation units closer to those areas. In this paper, we propose a computing continuum architecture for offloading distributed intelligences over cloud, edge and deep edge layers. Exploiting the federated learning paradigm, enables mobile and stationary devices to independently train local models, contributing to the creation of the global common mode.

Natural disasters pose increasing threats to communities and economies worldwide, emphasizing the urgency for technological interventions to support first responders and decision-makers in affected areas. To address this need, we introduce a novel computing continuum architecture designed for efficient offloading of distributed intelligences across cloud, edge, and deep edge tiers. Our approach leverages an AI crosslayer framework, integrating service, network, and infrastructure management, to optimize decision-making processes in timesensitive disaster scenarios. By employing federated learning techniques, our architecture enables both mobile and stationary devices to autonomously train local models, contributing to the development of a comprehensive global common model. Through this collaborative approach, we aim to enhance the capabilities of disaster management systems, facilitating more effective responses to critical events.