activity
20232026
most citedExtending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions

4 citations · 4 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2026

Shifting-based Optimizable Linear Relaxations for General Activation Functions

Philipp Kern, László Antal, Erika Ábráham +1

The use of neural networks (NNs) is rapidly increasing, including in safety- and security-critical domains. To provide formal guarantees about NN behavior, many verification method…

cs.CV2024

ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection

Martin Aubard, László Antal, Ana Madureira +2

This paper introduces ROSAR, a novel framework enhancing the robustness of deep learning object detection models tailored for side-scan sonar (SSS) images, generated by autonomous…

cs.CV2024

Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detection

Martin Aubard, László Antal, Ana Madureira +1

In this paper we present YOLOX-ViT, a novel object detection model, and investigate the efficacy of knowledge distillation for model size reduction without sacrificing performance.…

cs.RO2024

Mission Planning and Safety Assessment for Pipeline Inspection Using Autonomous Underwater Vehicles: A Framework based on Behavior Trees

Martin Aubard, Sergio Quijano, Olaya Álvarez-Tuñón +3

The recent advance in autonomous underwater robotics facilitates autonomous inspection tasks of offshore infrastructure. However, current inspection missions rely on predefined pla…

cs.RO2024

SubPipe: A Submarine Pipeline Inspection Dataset for Segmentation and Visual-inertial Localization

Olaya Álvarez-Tuñón, Luiza Ribeiro Marnet, László Antal +3

This paper presents SubPipe, an underwater dataset for SLAM, object detection, and image segmentation. SubPipe has been recorded using a \gls{LAUV}, operated by OceanScan MST, and…

cs.LG20234 cited

Extending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions

László Antal, Hana Masara, Erika Ábrahám

In this paper, we extend an available neural network verification technique to support a wider class of piece-wise linear activation functions. Furthermore, we extend the algorithm…