8 papers
SAM3-O2D2: Zero-Shot Object Out-of-Distribution Detection by Object Class Prompting of the SAM3-Image Model
Lucas Görnhardt, Timo Bartels, Tim Fingscheidt
Object detectors have shown remarkable performance in various fields, among these medical imaging, surveillance, and autonomous driving. However, they are prone to overconfidence w…
Distributed Semantic Segmentation With Improved Rate-Distortion Trade-Off
Danish Nazir, Timo Bartels, Thorsten Bagdonat +1
Distributed deep neural networks (DNNs) for dense perception tasks such as semantic segmentation execute an encoder DNN on edge devices, and a decoder DNN typically on a large-scal…
StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruning
Timo Bartels, Danish Nazir, Jan Piewek +2
Structured pruning enhances the efficiency of deep neural networks (DNNs) by eliminating groups of parameters during inference. Previous methods mostly reduce computational complex…
Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation
Lucas Görnhardt, Timo Bartels, Niklas Schwarz +1
Conventional one-hot encodings often yield poorly calibrated models, being overconfident under attack, and letting entropy-based detection algorithms fail. Previous image classific…
Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning
Danish Nazir, Antoine Hanna-Asaad, Lucas Görnhardt +3
Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being com…
An Efficient Semantic Segmentation Decoder for In-Car or Distributed Applications
Danish Nazir, Gowtham Sai Inti, Timo Bartels +3
Modern automotive systems leverage deep neural networks (DNNs) for semantic segmentation and operate in two key application areas: (1) In-car, where the DNN solely operates in the…