Fine Grained Image Classification On Cub 200 1
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| three-branch-and-mutil-scale-learning-for | 89.6 |
| feature-boosting-suppression-and | 89.5 |
| towards-faster-training-of-global-covariance | 88.7 |
| revisiting-weakly-supervised-pre-training-of | 91.7 |
| are-these-birds-similar-learning-branched | 87.5 |
| learning-multi-attention-convolutional-neural | 86.5 |
| learning-a-discriminative-filter-bank-within | 87.4 |
| pairwise-confusion-for-fine-grained-visual | 86.9 |
| looking-for-the-devil-in-the-details-learning | 87.9 |
| align-yourself-self-supervised-pre-training | 77.1 |
| context-aware-attentional-pooling-cap-for | 91.8 |
| towards-class-specific-unit | 88.5 |
| domain-adaptive-transfer-learning-on-visual | 91.2 |
| look-into-object-self-supervised-structure | 88.0 |
| counterfactual-attention-learning-for-fine | 90.6 |
| advisingnets-learning-to-distinguish-correct | 88.59 |
| unlabeled-samples-generated-by-gan-improve | 84.4 |
| feature-fusion-vision-transformer-fine | 91.6 |
| see-better-before-looking-closer-weakly | 89.4 |
| high-order-interaction-for-weakly-supervised | 90.02% |
| fixing-the-train-test-resolution-discrepancy | 88.7 |
| deformable-part-descriptors-for-fine-grained | 50.98 |
| a-novel-plug-in-module-for-fine-grained-1 | 92.8 |
| fine-grained-visual-classification-with-high-1 | 93.1% |
| a-simple-episodic-linear-probe-improves | 88.8 |
| transfg-a-transformer-architecture-for-fine | 91.7 |