Object Detection on Fruits images (test)
12.32AP50CropVLM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CropVLMType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 12.32 | 7.27 | |
| DetProType=Open Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 11.87 | 7.61 | |
| GDINOType=Open Vocabulary, Backbone=ViT, Protocol=zero-shot2026.05 | 11.5 | 5.5 | |
| OV-DETRType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 11.35 | 5.94 | |
| DETRType=Closed Vocabulary, Backbone=ResNet101, Protocol=zero-shot2026.05 | 10.82 | 5.71 | |
| YOLOv9Type=Closed Vocabulary, Backbone=CSPDarknet-X, Protocol=zero-shot2026.05 | 10.01 | 5.1 | |
| RNCDLType=Open Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 9.77 | 4.99 | |
| YOLOv8Type=Closed Vocabulary, Backbone=CSPDarknet53, Protocol=zero-shot2026.05 | 9.07 | 4.47 | |
| RCNNType=Closed Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 8.99 | 3.62 | |
| CFMType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 8.39 | 4.72 |