Common corruptions for evaluating and enhancing robustness in air-to-air visual object detection

A Arsenos, V Karampinis… - IEEE Robotics and …, 2024 - ieeexplore.ieee.org
The main barrier to achieving fully autonomous flights lies in autonomous aircraft navigation.
Managing non-cooperative traffic presents the most important challenge in this problem. The …

Physical Adversarial Attacks Against Aerial Object Detection With Feature-Aligned Expandable Textures

Y Zhang, J Chen, Z Peng, Y Dang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Physical adversarial attacks in aerial object detection have gained significant attention.
Existing adversarial patches exhibit subpar visual effects and encounter limitations when …

Discretization and decoupled knowledge distillation for arbitrary oriented object detection

C Chen, H Ding, M Duan - Digital Signal Processing, 2024 - Elsevier
In recent years, lightweight object detection networks have been increasingly applied to
remote sensing platforms due to their fast inference speed and flexible deployment …

Clip-guided source-free object detection in aerial images

N Liu, X Xu, Y Su, C Liu, P Gong… - IGARSS 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Domain adaptation is crucial in aerial imagery, as the visual representation of these images
can significantly vary based on factors such as geographic location, time, and weather …

Common Corruptions for Enhancing and Evaluating Robustness in Air-to-Air Visual Object Detection

A Arsenos, V Karampinis, E Petrongonas… - arxiv preprint arxiv …, 2024 - arxiv.org
The main barrier to achieving fully autonomous flights lies in autonomous aircraft navigation.
Managing non-cooperative traffic presents the most important challenge in this problem. The …

[PDF][PDF] Ευρωστία σε εκτός κατανομής δεδομένα για κρίσιμες εφαρμογές της όρασης υπολογιστών

Α Αρσένος - 2025 - dspace.lib.ntua.gr
Artificial intelligence (AI) has progressed explosively in recent years. Driven by the advent of
deep learning, AI is being used in a variety of applications, across multiple scientific fields, in …