Konstantinos Georgiou

Stefan Dobrev, Konstantinos Georgiou, Evangelos Kranakis et al.

We study a problem of online targets coverage by a drone or a sensor that is equipped with a camera or an antenna of fixed half-angle of view $α$. The targets to be monitored appear at arbitrary positions on a line barrier in an online manner. When a new target appears, the drone has to move to a location that covers the newly arrived target, as well as already existing targets. The objective is to design a coverage algorithm that optimizes the total length of the drone's trajectory. Our results are reported in terms of an algorithm's competitive ratio, i.e., the worst-case ratio (over all inputs) of its cost to that of an optimal offline algorithm. In terms of upper bounds, we present three online algorithms and prove bounds on their competitive ratios for every $α\in [0, π/2]$. The best of them, called \FA is significantly better than the other two for $π/6 < α< π/3$. In particular, for $α=π/4$, its worst case, \FA has competitive ratio $1.25$, while the other two have competitive ratio $\sqrt{2}$. Finally, we prove a lower bound on the competitive ratio of online algorithms for a drone with half-angle $α\in [0, π/4]$; this bound is a function of $α$ that achieves its maximum value at $α= π/4$ equal to $(1+\sqrt{2})/2 \approx 1.207$.

Maofeng Tang, Andrei Cozma, Konstantinos Georgiou et al.

Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images. This paper revisits the classical multi-scale representation learning problem but under the general framework of self-supervised learning for remote sensing image understanding. We present Cross-Scale MAE, a self-supervised model built upon the Masked Auto-Encoder (MAE).During pre-training, Cross-Scale MAE employs scale augmentation techniques and enforces cross-scale consistency constraints through both contrastive and generative losses to ensure consistent and meaningful representations well-suited for a wide range of downstream tasks. Further, our implementation leverages the xFormers library to accelerate network pre-training on a single GPU while maintaining the quality of learned representations. Experimental evaluations demonstrate that Cross-Scale MAE exhibits superior performance compared to standard MAE and other state-of-the-art remote sensing MAE methods.

Konstantinos Georgiou, Maofeng Tang, Hairong Qi

Masked image modeling (MIM) methods typically operate in either raw pixel space (reconstructing masked patches) or latent feature space (aligning with a pre-trained teacher). We present MEDiC (Multi-objective Exploration of Distillation from CLIP), a framework that combines both spaces in a single pipeline through three complementary objectives: patch-level token distillation from a frozen CLIP encoder, global CLS alignment, and pixel reconstruction via a lightweight decoder. We conduct a systematic investigation of the design space surrounding this multi-objective framework. First, we show that all three objectives provide complementary information, with the full combination reaching 73.9% kNN accuracy on ImageNet-1K. Second, we introduce hierarchical clustering with relative position bias for evolved masking and find that, despite producing more semantically coherent masks than prior methods, evolved masking does not outperform simple block masking in the teacher-guided distillation setting, a finding we attribute to the teacher's inherent semantic awareness. Third, we reveal that optimal scalar loss weights are extremely fragile, with small perturbations causing drops of up to 17 percentage points in kNN accuracy. Our framework achieves 73.9% kNN and 85.1% fine-tuning accuracy with ViT-Base at 300 epochs.

Ran Elgedawy, Porter Dosch, John Sadik et al.

$ $Large Language Models (LLMs) are being increasingly utilized in various applications, with code generations being a notable example. While previous research has shown that LLMs have the capability to generate both secure and insecure code, the literature does not take into account what factors help generate secure and effective code. Therefore in this paper we focus on identifying and understanding the conditions and contexts in which LLMs can be effectively and safely deployed in real-world scenarios to generate quality code. We conducted a comparative analysis of four advanced LLMs--GPT-3.5 and GPT-4 using ChatGPT and Bard and Gemini from Google--using 9 separate tasks to assess each model's code generation capabilities. We contextualized our study to represent the typical use cases of a real-life developer employing LLMs for everyday tasks as work. Additionally, we place an emphasis on security awareness which is represented through the use of two distinct versions of our developer persona. In total, we collected 61 code outputs and analyzed them across several aspects: functionality, security, performance, complexity, and reliability. These insights are crucial for understanding the models' capabilities and limitations, guiding future development and practical applications in the field of automated code generation.

Konstantinos Georgiou, Nikolaos Mittas, Lefteris Angelis et al.

The Covid-19 outbreak, beyond its tragic effects, has changed to an unprecedented extent almost every aspect of human activity throughout the world. At the same time, the pandemic has stimulated enormous amount of research by scientists across various disciplines, seeking to study the phenomenon itself, its epidemiological characteristics and ways to confront its consequences. Information Technology, and particularly Data Science, drive innovation in all related to Covid-19 biomedical fields. Acknowledging that software developers routinely resort to open question and answer communities like Stack Overflow to seek advice on solving technical issues, we have performed an empirical study to investigate the extent, evolution and characteristics of Covid-19 related posts. In particular, through the study of 464 Stack Overflow questions posted mainly in February and March 2020 and leveraging the power of text mining, we attempt to shed light into the interest of developers in Covid-19 related topics and the most popular technological problems for which the users seek information. The findings reveal that indeed this global crisis sparked off an intense and increasing activity in Stack Overflow with most post topics reflecting a strong interest on the analysis of Covid-19 data, primarily using Python technologies.