3 papers
cs.CV2025
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…
cs.LG2025
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…
eess.IV2024
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…