Fine-grained image classification on FGVC Aircraft (test)
75.6Base AccuracyToolFG
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ToolFGTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | 75.6 | 76.5 | 76.1 | |
| DiVE-kTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | 68.1 | 69.1 | 68.6 | |
| Fine-R1Training Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | 66.8 | 69.7 | 68.2 | |
| ViRFTTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | 66.4 | 67.8 | 67.1 | |
| Qwen2.5-VL-7BTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | 50.3 | 54.3 | 52.3 | |
| PromptSRCTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | 42.7 | 37.9 | 40.2 | |
| MaPLeTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | 37.4 | 35.6 | 36.5 |