Fine Grained Image Classification On Stanford 1
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| 2003-13549 | 61.2% |
| advisingnets-learning-to-distinguish-correct | 86.31% |
| a-continual-development-methodology-for-large | 93.5% |
| transfg-a-transformer-architecture-for-fine | 92.3% (90.6%) |
| understanding-gaussian-attention-bias-of | 90.185% |
| fine-grained-visual-classification-via-2 | 91.8% |
| sim-ofe-structure-information-mining-and | 93.3% |
| fine-grained-visual-classification-using-self | 93.1% |
| vit-net-interpretable-vision-transformers | 93.6% |
| fine-grained-recognition-accounting-for | 87.7% |
| learning-attentive-pairwise-interaction-for | 90.3% |
| multi-granularity-part-sampling-attention-for | 95.4% |
| on-the-eigenvalues-of-global-covariance | 93.0% |
| rams-trans-recurrent-attention-multi-scale | 92.4% |
| a-free-lunch-from-vit-adaptive-attention | 91.6% |
| pairwise-confusion-for-fine-grained-visual | 83.75% |
| domain-adaptive-transfer-learning-on-visual | 90% |
| feature-fusion-vision-transformer-fine | 91.5% |
| an-attention-locating-algorithm-for | 91.1% |
| transformer-with-peak-suppression-and | 92.5% |
| delving-into-multimodal-prompting-for-fine | 91.0% |
| sr-gnn-spatial-relation-aware-graph-neural | 97.3% |
| learning-semantically-enhanced-feature-for | 88.8% |