A5076427679- Infrared Thermography in Medicine
- Reinforcement Learning in Robotics
- Ultrasound Imaging and Elastography
- Digital Radiography and Breast Imaging
- Fault Detection and Control Systems
- Radiomics and Machine Learning in Medical Imaging
- Stochastic Gradient Optimization Techniques
- Control Systems and Identification
- Real-time simulation and control systems
- COVID-19 diagnosis using AI
- Advanced Bandit Algorithms Research
- Advanced Neural Network Applications
Siemens Healthcare (Germany)
2023
Friedrich-Alexander-Universität Erlangen-Nürnberg
2022
Fine-tuning large pre-trained foundation models, such as the 175B GPT-3, has attracted more attention for downstream tasks recently. While parameter-efficient fine-tuning methods have been proposed and proven effective without retraining all model parameters, their performance is limited by capacity of incremental modules, especially under constrained parameter budgets. \\ To overcome this challenge, we propose CapaBoost, a simple yet strategy that enhances leveraging low-rank updates...
Implicit models such as Deep Equilibrium Models (DEQs) have garnered significant attention in the community for their ability to train infinite layer with elegant solution-finding procedures and constant memory footprint. However, despite several attempts, these methods are heavily constrained by model inefficiency optimization instability. Furthermore, fair benchmarking across relevant vision tasks is missing. In this work, we revisit line of implicit trace them back original weight-tied...