Object Detection on Tropical Fruits (test)
50.73AP50CropVLM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CropVLMType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 50.73 | 46.03 | |
| GDINOType=Open Vocabulary, Backbone=ViT, Protocol=zero-shot2026.05 | 34.89 | 34.89 | |
| CFMType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 32.31 | 25.82 | |
| RCNNType=Closed Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 24.75 | 24.31 | |
| RNCDLType=Open Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 24.69 | 24.39 | |
| DETRType=Closed Vocabulary, Backbone=ResNet101, Protocol=zero-shot2026.05 | 24.68 | 24.49 | |
| OV-DETRType=Open Vocabulary, Backbone=ResNet50 + ViT, Protocol=zero-shot2026.05 | 24.1 | 24.45 | |
| YOLOv8Type=Closed Vocabulary, Backbone=CSPDarknet53, Protocol=zero-shot2026.05 | 23.54 | 23.37 | |
| DetProType=Open Vocabulary, Backbone=ResNet50, Protocol=zero-shot2026.05 | 22.47 | 18.57 | |
| YOLOv9Type=Closed Vocabulary, Backbone=CSPDarknet-X, Protocol=zero-shot2026.05 | 16.08 | 16.08 |