David Rohrschneider
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
David Rohrschneider has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Uwe Handmann
Ruhr West University of Applied Science
3 shared publications - Nermeen Abou Baker
Ruhr West University of Applied Sciences
2 shared publications - Marc Jansen1 shared publication
- Marcel Pehlke1 shared publication
Latest Publications
- Open Access
- 24 February 2026
- Published by Elsevier in Digital Business
- Vol. 6 (1)
LLM-based JSON Mapping and Blockchain Integration for Digital Product Passports
- 24 February 2026
- Published by Elsevier in Digital Business
- Vol. 6 (1)
Open AccessLLM-based JSON Mapping and Blockchain Integration for Digital Product Passports
- Open Access
- 2 December 2024
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 6 (4) , 2783-2807
Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks
Research and applications in artificial intelligence have recently shifted with the rise of large pretrained models, which deliver state-of-the-art results across numerous tasks. However, the substantial increase in parameters introduces a need for parameter-efficient training strategies. Despite significant advancements, limited research has explored parameter-efficient fine-tuning (PEFT) methods in the context of transformer-based models for instance segmentation. Addressing this gap, this study investigates the effectiveness of PEFT methods, specifically adapters and Low-Rank Adaptation (LoRA), applied to two models across four benchmark datasets. Integrating sequentially arranged adapter modules and applying LoRA to deformable attention—explored here for the first time—achieves competitive performance while fine-tuning only about 1–6% of model parameters, a marked improvement over the 40–55% required in traditional fine-tuning. Key findings indicate that using 2–3 adapters per transformer block offers an optimal balance of performance and efficiency. Furthermore, LoRA, exhibits strong parameter efficiency when applied to deformable attention, and in certain cases surpasses adapter configurations. These results show that the impact of PEFT techniques varies based on dataset complexity and model architecture, underscoring the importance of context-specific tuning. Overall, this work demonstrates the potential of PEFT to enable scalable, customizable, and computationally efficient transfer learning for instance segmentation tasks.
- 2 December 2024
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 6 (4) , 2783-2807
Open AccessParameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks
Research and applications in artificial intelligence have recently shifted with the rise of large pretrained models, which deliver state-of-the-art results across numerous tasks. However, the substantial increase in parameters introduces a need for parameter-efficient training strategies. Despite significant advancements, limited research has explored parameter-efficient fine-tuning (PEFT) methods in the context of transformer-based models for instance segmentation. Addressing this gap, this study investigates the effectiveness of PEFT methods, specifically adapters and Low-Rank Adaptation (LoRA), applied to two models across four benchmark datasets. Integrating sequentially arranged adapter modules and applying LoRA to deformable attention—explored here for the first time—achieves competitive performance while fine-tuning only about 1–6% of model parameters, a marked improvement over the 40–55% required in traditional fine-tuning. Key findings indicate that using 2–3 adapters per transformer block offers an optimal balance of performance and efficiency. Furthermore, LoRA, exhibits strong parameter efficiency when applied to deformable attention, and in certain cases surpasses adapter configurations. These results show that the impact of PEFT techniques varies based on dataset complexity and model architecture, underscoring the importance of context-specific tuning. Overall, this work demonstrates the potential of PEFT to enable scalable, customizable, and computationally efficient transfer learning for instance segmentation tasks.
- 30 September 2023
- Published by Springer Nature
- p. 175-188
Double Transfer Learning to Detect Lithium-Ion Batteries on X-Ray Images
- 30 September 2023
- Published by Springer Nature
- p. 175-188
Double Transfer Learning to Detect Lithium-Ion Batteries on X-Ray Images