8 papers
Comfortably Stuck: Evaluation Pitfalls in Bench2Drive's Closed-Loop Protocol
Thomas Schwarzfischer, Emad Aghajanzadeh, Moritz Thoma +5
Closed-loop evaluation is widely regarded as a more faithful way to assess end-to-end (E2E) driving models than open-loop evaluation, and Bench2Drive, built on the CARLA simulator,…
Mind the Approximation: Fisher-Weighted SVD Compression for ViTs
Moritz Thoma, Maximilian Groezinger, Maximilian Forstenhäusler +7
Model compression is key to mitigate deployment challenges of ever growing machine learning models. In this area of research, singular value decomposition (SVD)-based compression o…
HiFi-LLP: High-Fidelity, Low-Cost Latency Predictors with Confidence for Robust HW-NAS
Shambhavi Balamuthu Sampath, Behzad Shomali, Nael Fasfous +7
With deep neural networks (DNNs) increasingly deployed on edge devices, hardware (HW)-aware optimization techniques--such as HW-aware compression and HW-aware neural architecture s…
BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks
Manoj Rohit Vemparala, Alexander Frickenstein, Nael Fasfous +8
Deploying convolutional neural networks (CNNs) for embedded applications presents many challenges in balancing resource-efficiency and task-related accuracy. These two aspects have…
BinaryCoP: Binary Neural Network-based COVID-19 Face-Mask Wear and Positioning Predictor on Edge Devices
Nael Fasfous, Manoj-Rohit Vemparala, Alexander Frickenstein +2
Face masks have long been used in many areas of everyday life to protect against the inhalation of hazardous fumes and particles. They also offer an effective solution in healthcar…
L2PF -- Learning to Prune Faster
Manoj-Rohit Vemparala, Nael Fasfous, Alexander Frickenstein +6
Various applications in the field of autonomous driving are based on convolutional neural networks (CNNs), especially for processing camera data. The optimization of such CNNs is a…