Accurate weed detection plays a crucial role in sustainable crop management, enabling targeted interventions that reduce chemical use and improve yield. Deep learning-based weed detection and targeted, site-specific weed management offer significant opportunities for resource and environmental conservation in agriculture. However, current state-of-the-art (SOTA) deep learning models are typically trained on narrow, task-specific datasets and perform poorly when exposed to new, unseen field conditions. This is due to the inherently heterogeneous nature of weed detection data, which for instance varies across crop types, growth stages, soil conditions, imaging modalities, and environmental factors. These models also often suffer from being highly data-hungry, requiring large volumes of labeled data to function effectively. Collecting such data in agriculture is costly and time-consuming. Therefore, there is a pressing need for more data-efficient and generalizable approaches.
In this regard, we aim to explore and validate the hypothesis that pretrained foundation models, which have learned general visual features from large and diverse datasets, can be fine-tuned for weed detection with significantly less labeled data, while maintaining or improving performance compared to traditional SOTA models. These models are hypothesized to be less sensitive to data heterogeneity and capable of generalizing well, thereby enabling broader applicability in real-world agricultural conditions.
Towards data efficient and robust weed detection leveraging foundational models.
MEMBER IN THE JOINT ACADEMIC PARTNERSHIP
since
Joint Academic Partnership Life Sciences and Green Technologies
Prof. Dr. agr. Heinz Bernhardt
Stable 4.0 (Integrated Dairy Farming)
Current research projects
- Animal-Machine Interaction
- Influencing Factors Analysis on Infield Logistics
- Precision Grassland Farming
- Automatic Feeding Systems for Cattle
- Modeling agricultural transport logistics
- Simulation agricultural crop chains
Projects:
- Vorhersage der Akzeptanz bei Einführung eines On-Farm-Energiemanagementsystems im automatisierten Milchviehstall unter Berücksichtigung demographischer und sozioökonomischer Auswirkungen auf Gesellschaft und den ländlichen Raum
- Foundations for implementing an on-farm energy management system in the dairy cattle farm
Prof. Dr. Florian Haselbeck
The Professorship of Smart Farming at Weihenstephan-Triesdorf University of Applied Sciences, headed by Florian Haselbeck, conducts research on AI-based methods for various applications in a sustainability context. The team's main focus is on developing computer vision and time series forecasting methods as well as multimodal machine learning approaches to create practical and scientifically sound solutions in close collaboration with domain experts.
Project:
Harshavardhan Subramanian
Weihenstephan-Triesdorf University of Applied Sciences
Master: Statistics and Machine Learning, Linköping University, Sweden
Bachelor: Industrial Engineering and Management, Visvesvaraya Technological University, India
Publication: Bukas, Christina, Harshavardhan Subramanian, Fenja See, Carina Steinchen, Ivan Ezhov, Gowtham Boosarpu, Sara
Asgharpour et al. ”MultiOrg: A Multi-rater Organoid-detection Dataset.” Advances in Neural Information Processing
Systems 37 (2024): 95808-95839.
