Domain Generalization for Crop Segmentation with Knowledge Distillation

Paper: Angarano, S., Martini, M., Navone, A., & Chiaberge, M. (2023). Domain Generalization for Crop Segmentation with Knowledge Distillation. Accepted at ECML PKDD 2023 Workshop “Adapting to Change: Reliable Learning Across Domains”. 

Poster: Domain Generalization for Crop Segmentation with Knowledge Distillation

Code: https://github.com/PIC4SeR/AgriSeg



AgriSeg - A Multi-domain Dataset for Sim-to-Real Crop Segmentation

AgriSeg contains 11 crop types and covers different terrain styles, weather conditions, and light scenarios for more than 50,000 samples.

Paper: Martini, M., Eirale, A., Tuberga, B., Ambrosio, M., Ostuni, A., Messina, F., Mazzara, L., Chiaberge, M. (2023), Enhancing Navigation Benchmarking and Perception Data Generation for Row-based Crops in Simulation. Precision Agriculture ‘23 (pp. 451-457). Wageningen Academic.

[ Download AgriSeg ]
The link is protected. To request access, please contact simone.angarano@polito.it