Fine-grained Visual Classification on Oxford-IIIT Pet (test)
88.97Top-1 AccuracyPAND
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| PANDStudent=ResNet-182026.02 | 88.97 | — | — | — | |
| VL2LiteStudent=ResNet-182026.02 | 88.56 | — | — | — | |
| PANDStudent=MobileNet-V22026.02 | 88.28 | — | — | — | |
| VL2LiteStudent=MobileNet-V22026.02 | 87.55 | — | — | — | |
| RKDStudent=ResNet-182026.02 | 86.94 | — | — | — | |
| KDStudent=ResNet-182026.02 | 86.74 | — | — | — | |
| RKDStudent=MobileNet-V22026.02 | 86.56 | — | — | — | |
| KDStudent=MobileNet-V22026.02 | 86.07 | — | — | — | |
| w/o KDStudent=ResNet-182026.02 | 84.94 | — | — | — | |
| w/o KDStudent=MobileNet-V22026.02 | 84.07 | — | — | — | |
| DiVE-kTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | — | 89.1 | 94.2 | 91.6 | |
| Fine-R1Training Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | — | 90.9 | 93 | 92 | |
| MaPLeTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | — | 95.4 | 97.8 | 96.6 | |
| PromptSRCTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | — | 95.3 | 97.3 | 96.3 | |
| Qwen2.5-VL-7BTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | — | 87.5 | 93.3 | 90.3 | |
| ToolFGTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | — | 96.8 | 99.7 | 98.2 | |
| ViRFTTraining Strategy=per-dataset training, Evaluation Protocol=Zero-shot base-to-novel generalization2026.06 | — | 92.6 | 92.8 | 92.7 |