10 citations · 13 across the 5 of their papers we have counts for
7 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,…
Hybrid Convolution and Vision Transformer NAS Search Space for TinyML Image Classification
Mikhael Djajapermana, Moritz Reiber, Daniel Mueller-Gritschneder +1
Hybrids of Convolutional Neural Network (CNN) and Vision Transformer (ViT) have outperformed pure CNN or ViT architecture. However, since these architectures require large paramete…
A High-Level Compiler Integration Approach for Deep Learning Accelerators Supporting Abstraction and Optimization
Samira Ahmadifarsani, Daniel Mueller-Gritschneder, Ulf Schlichtmann
The growing adoption of domain-specific architectures in edge computing platforms for deep learning has highlighted the efficiency of hardware accelerators. However, integrating cu…
EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation
Nikolai Körber, Eduard Kromer, Andreas Siebert +3
We introduce EGIC, an enhanced generative image compression method that allows traversing the distortion-perception curve efficiently from a single model. EGIC is based on two nove…
TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning
Marcus Rüb, Daniel Maier, Daniel Mueller-Gritschneder +1
Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on…
MLonMCU: TinyML Benchmarking with Fast Retargeting
Philipp van Kempen, Rafael Stahl, Daniel Mueller-Gritschneder +1
While there exist many ways to deploy machine learning models on microcontrollers, it is non-trivial to choose the optimal combination of frameworks and targets for a given applica…
Fused Depthwise Tiling for Memory Optimization in TinyML Deep Neural Network Inference
Rafael Stahl, Daniel Mueller-Gritschneder, Ulf Schlichtmann
Memory optimization for deep neural network (DNN) inference gains high relevance with the emergence of TinyML, which refers to the deployment of DNN inference tasks on tiny, low-po…