Thoma, Moritz

5 publications

CVPRW 2025 FLAR-SVD: Fast and Latency-Aware Singular Value Decomposition for Model Compression Moritz Thoma, Jorge Villasante, Emad Aghajanzadeh, Shambhavi Balamuthu Sampath, Pierpaolo Morì, Maximilian Groetzinger, Daniil Dylkin, Manoj Rohit Vemparala, Nael Fasfous, Alexander Frickenstein, Daniel Mueller-Gritschneder, Ulf Schlichtmann

CVPRW 2025 RepFC: Universal Structural Reparametrization Block for High Performance, Lightweight Deep Neural Networks Shambhavi Balamuthu Sampath, Judeson Anthony Fernando, Moritz Thoma, Nael Fasfous, Lukas Frickenstein, Pierpaolo Morì, Manoj Rohit Vemparala, Alexander Frickenstein, Ulf Schlichtmann, Walter Stechele

CVPRW 2025 Uncertainty Aware Training to Improve Uncertainty Active Learning for Semantic Segmentation Moritz Thoma, Tobias Preintner, Emad Aghajanzadeh, Shambhavi Balamuthu Sampath, Pierpaolo Morì, Nael Fasfous, Manoj Rohit Vemparala, Alexander Frickenstein, Daniel Mueller-Gritschneder, Ulf Schlichtmann

CVPRW 2024 Pruning as a Binarization Technique Lukas Frickenstein, Pierpaolo Morì, Shambhavi Balamuthu Sampath, Moritz Thoma, Nael Fasfous, Manoj Rohit Vemparala, Alexander Frickenstein, Christian Unger, Claudio Passerone, Walter Stechele

WACV 2024 Wino Vidi Vici: Conquering Numerical Instability of 8-Bit Winograd Convolution for Accurate Inference Acceleration on Edge Pierpaolo Mori, Lukas Frickenstein, Shambhavi Balamuthu Sampath, Moritz Thoma, Nael Fasfous, Manoj Rohit Vemparala, Alexander Frickenstein, Christian Unger, Walter Stechele, Daniel Mueller-Gritschneder, Claudio Passerone