Sotirios Konstantakos

Sotirios Konstantakos, Despina Ioanna Chalkiadaki, Ioannis Mademlis et al.

Automated visual firearms classification from RGB images is an important real-world task with applications in public space security, intelligence gathering and law enforcement investigations. When applied to images massively crawled from the World Wide Web (including social media and dark Web sites), it can serve as an important component of systems that attempt to identify criminal firearms trafficking networks, by analyzing Big Data from open-source intelligence. Deep Neural Networks (DNN) are the state-of-the-art methodology for achieving this, with Convolutional Neural Networks (CNN) being typically employed. The common transfer learning approach consists of pretraining on a large-scale, generic annotated dataset for whole-image classification, such as ImageNet-1k, and then finetuning the DNN on a smaller, annotated, task-specific, downstream dataset for visual firearms classification. Neither Visual Transformer (ViT) neural architectures nor Self-Supervised Learning (SSL) approaches have been so far evaluated on this critical task..

Sotirios Konstantakos, Jorgen Cani, Ioannis Mademlis et al.

Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a 'pretext task' that does not require ground-truth labels/annotation. This allows efficient representation learning from massive amounts of unlabeled training data, which in turn leads to increased accuracy in a 'downstream task' by exploiting supervised transfer learning. Despite the relatively straightforward conceptualization and applicability of SSL, it is not always feasible to collect and/or to utilize very large pretraining datasets, especially when it comes to real-world application settings. In particular, in cases of specialized and domain-specific application scenarios, it may not be achievable or practical to assemble a relevant image pretraining dataset in the order of millions of instances or it could be computationally infeasible to pretrain at this scale, e.g., due to unavailability of sufficient computational resources that SSL methods typically require to produce improved visual analysis results. This situation motivates an investigation on the effectiveness of common SSL pretext tasks, when the pretraining dataset is of relatively limited/constrained size. This work briefly introduces the main families of modern visual SSL methods and, subsequently, conducts a thorough comparative experimental evaluation in the low-data regime, targeting to identify: a) what is learnt via low-data SSL pretraining, and b) how do different SSL categories behave in such training scenarios. Interestingly, for domain-specific downstream tasks, in-domain low-data SSL pretraining outperforms the common approach of large-scale pretraining on general datasets.

Sotirios Konstantakos, Sotirios Asparagkathos, Moatasim Mahmoud et al.

In the context of increasing urban risks, particularly from climate change-induced flooding, this paper presents an extended Reality (XR)-based framework to improve user risk training within urban built environments. The framework is designed to improve risk awareness and preparedness among various stakeholders, including citizens, local authorities, and emergency responders. Using immersive XR technologies, the training experience simulates real-world emergency scenarios, contributing to active participation and a deeper understanding of potential hazards and especially for floods. The framework highlights the importance of stakeholder participation in its development, ensuring that training modules are customized to address the specific needs of different user groups. The iterative approach of the framework supports ongoing refinement through user feedback and performance data, thus improving the overall effectiveness of risk training initiatives. This work outlines the methodological phases involved in the framework's implementation, including i) user flow mapping, ii) scenario selection, and iii) performance evaluation, with a focus on the pilot application in Senigallia, Italy. The findings underscore the potential of XR technologies to transform urban risk training, promoting a culture of preparedness and resilience against urban hazards.