Research map / Detection and segmentation / Open-set and few-shot detection
PhenoBench: A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain
Jan Weyler, Federico Magistri, Elias Marks, Yue Linn Chong, Matteo Sodano, Gianmarco Roggiolani, Nived Chebrolu, Cyrill Stachniss, Jens Behley
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ERFNet (2.1 M params) instead of DeepLabV3+ (39.8 M params) | semantic segmentation baseline · PhenoBench semantic segmentation (test) | mIoU: 85.98 vs 85.97 | No clear effect |
| use Mask2Former instead of Mask R-CNN | panoptic segmentation · PhenoBench panoptic segmentation (test) | PQ†: 65.79 -> 69.99 | Improved |
| use Mask2Former instead of Panoptic DeepLab | panoptic segmentation · PhenoBench panoptic segmentation (test) | PQ†: 57.97 -> 69.99 | Improved |
| use YOLOv7 instead of Faster R-CNN | plant detection · PhenoBench plant detection (test) | mAP: 40.43 -> 60.48 | Improved |
| use YOLOv7 instead of Faster R-CNN | leaf detection · PhenoBench leaf detection (test) | mAP: 33.91 -> 57.90 | Improved |
| detect weeds instead of crops | YOLOv7 · PhenoBench plant detection (test) | AP: 83.06 -> 37.91 | Hurt |
| detect leaves instead of plants | YOLOv7 · PhenoBench detection (test) | mAP: 60.48 -> 57.90 | Hurt |
| use Mask R-CNN instead of Mask2Former for leaf instances | leaf instance segmentation · PhenoBench leaf instance segmentation (test) | PQ leaf: 57.50 -> 59.74 | Improved |
| segment weeds instead of crops | ERFNet · PhenoBench semantic segmentation (test) | IoU: 94.30 -> 64.37 | Hurt |
| use HAPT instead of Weyler et al. | hierarchical panoptic segmentation · PhenoBench hierarchical panoptic segmentation (test) | PQ: 40.49 -> 50.73 | Improved |
Closest papers by meaning
- AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark (NeurIPS 2025 · similarity 0.90)
- AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning (NeurIPS 2026 · similarity 0.88)
- Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind (NeurIPS 2025 · similarity 0.87)
- Combining Deep Learning and Street View Imagery to Map Smallholder Crop Types (AAAI 2024 · similarity 0.86)
- Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding (CVPR 2024 · similarity 0.85)
- Fields of The World: A Machine Learning Benchmark Dataset for Global Agricultural Field Boundary Segmentation (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
