Fine Grained Image Classification On Fgvc
Métriques
Accuracy
FLOPS
PARAMS
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy | FLOPS | PARAMS |
|---|---|---|---|
| neural-architecture-transfer | 89.0% | 235M | 3.4M |
| see-better-before-looking-closer-weakly | 93.0% | - | - |
| progressive-co-attention-network-for-fine | 92.8% | - | - |
| fine-grained-visual-classification-via | 93.4% | - | - |
| compounding-the-performance-improvements-of | 92.4 | - | - |
| neural-architecture-transfer | 90.1% | 388M | 5.1M |
| counterfactual-attention-learning-for-fine | 94.2 | - | - |
| fine-grained-visual-classification-with-batch | 93.5% | - | - |
| towards-class-specific-unit | 94.0 % | - | - |
| attention-convolutional-binary-neural-tree | 92.4% | - | - |
| non-binary-deep-transfer-learning-for | 95.11 | - | - |
| the-devil-is-in-the-channels-mutual-channel | 92.9% | - | - |
| learning-a-discriminative-filter-bank-within | 92.0% | - | - |
| attribute-mix-semantic-data-augmentation-for | 93.1% | - | - |
| dual-cross-attention-learning-for-fine | 93.3% | - | - |
| context-semantic-quality-awareness-network | 94.7% | - | - |
| sr-gnn-spatial-relation-aware-graph-neural | 95.4 | 9.8 | 30.9 |
| with-a-little-help-from-my-friends-nearest | 64.1 | - | - |
| elope-fine-grained-visual-classification-with | 93.5% | - | - |
| context-aware-attentional-pooling-cap-for | 94.9% | - | 34.2 |
| on-the-eigenvalues-of-global-covariance | 93.5 | - | - |
| towards-faster-training-of-global-covariance | 91.4% | - | - |
| alignment-enhancement-network-for-fine | 94.5% | - | - |
| cross-x-learning-for-fine-grained-visual | 92.7% | - | - |
| neural-architecture-transfer | 87.0% | 175M | 3.2M |
| learn-from-each-other-to-classify-better | 94.7% | - | - |
| fine-grained-visual-classification-using-self | 93.1% | - | - |
| universal-fine-grained-visual-categorization | 94.2% | - | - |
| learning-semantically-enhanced-feature-for | 92.1% | - | - |
| fine-grained-visual-classification-with | 94.1% | - | - |
| fine-grained-recognition-accounting-for | 93.5% | - | - |
| learning-multi-attention-convolutional-neural | 89.9 | - | - |
| part-guided-relational-transformers-for-fine | 94.6% | - | - |
| Modèle 34 | 93.8% | - | - |
| a-simple-episodic-linear-probe-improves | 92.7 | - | - |
| domain-adaptive-transfer-learning-on-visual | - | - | - |
| learning-to-navigate-for-fine-grained | 91.4% | - | - |
| penalizing-the-hard-example-but-not-too-much | 92.9% | - | - |
| efficientnet-rethinking-model-scaling-for | 92.9 | - | - |
| three-branch-and-mutil-scale-learning-for | 94.7% | - | - |
| neural-architecture-transfer | 90.8% | 581M | 5.3M |
| sharpness-aware-minimization-for-efficiently-1 | - | - | - |
| re-rank-coarse-classification-with-local | 94.1% | - | - |
| interweaving-insights-high-order-feature | 96.42% | - | - |
| grad-cam-guided-channel-spatial-attention | 93.42% | - | - |
| channel-interaction-networks-for-fine-grained-1 | 93.3% | - | - |
| align-yourself-self-supervised-pre-training | 87.27 | - | - |
| look-into-object-self-supervised-structure | 92.7% | - | - |
| graph-propagation-based-correlation-learning | 93.2% | - | - |
| advancing-fine-grained-classification-by | 94.5 | - | - |
| weakly-supervised-fine-grained-image-1 | 93.8% | - | - |
| vision-models-are-more-robust-and-fair-when | 54.82% | - | - |
| your-labrador-is-my-dog-fine-grained-or-not | 93.6% | - | - |
| learning-attentive-pairwise-interaction-for | 93.9% | - | - |
| your-diffusion-model-is-secretly-a-zero-shot | 26.4 | - | - |
| autoaugment-learning-augmentation-policies | 92.67% | - | - |
| selective-sparse-sampling-for-fine-grained | 92.8% | - | - |