Object Detection on Diverse Fruits (test)
27.47AP@50CropVLM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CropVLMType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 27.47 | 19.93 | |
| DetProType=Open Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 25.95 | 22.36 | |
| CFMType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 11.48 | 9.37 | |
| OV-DETRType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 10.6 | 9.79 | |
| RNCDLType=Open Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 10.03 | 9.63 | |
| RCNNType=Closed Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 9.94 | 9.43 | |
| YOLOv8Type=Closed Vocabulary, Backbone=CSPDarknet53, Protocol=zero-shot2026.05 | 8.22 | 8.02 | |
| GDINOType=Open Vocabulary, Backbone=ViT, Protocol=zero-shot2026.05 | 8.19 | 7.76 | |
| DETRType=Closed Vocabulary, Backbone=ResNet101, Protocol=zero-shot2026.05 | 7.51 | 7.12 | |
| YOLOv9Type=Closed Vocabulary, Backbone=CSPDarknet-X, Protocol=zero-shot2026.05 | 5.36 | 5.15 |