Fine Grained Image Classification On Cub 200
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| delving-into-multimodal-prompting-for-fine | 91.8% |
| weakly-supervised-complementary-parts-models | 90.4% |
| graph-propagation-based-correlation-learning | 88.3% |
| learning-a-mixture-of-granularity-specific | 89.4% |
| learning-a-discriminative-filter-bank-within | 87.4% |
| fine-grained-visual-classification-with-batch | 89.2% |
| penalizing-the-hard-example-but-not-too-much | 88.2% |
| attribute-mix-semantic-data-augmentation-for | 90.2% |
| transifc-invariant-cues-aware-feature | 91.0% |
| context-aware-attentional-pooling-cap-for | 91.8% |
| visual-correspondence-based-explanations | 83.27 |
| snapmix-semantically-proportional-mixing-for | 89.58% |
| sim-trans-structure-information-modeling | 91.8% |
| learning-attentive-pairwise-interaction-for | 90.0% |
| transfg-a-transformer-architecture-for-fine | 91.7% |
| visual-correspondence-based-explanations | 84.98 |
| learning-semantically-enhanced-feature-for | 87.3% |
| channel-interaction-networks-for-fine-grained-1 | 88.3% |
| weakly-supervised-fine-grained-image-1 | 88.8% |
| human-attention-in-fine-grained | 88.66% |
| your-labrador-is-my-dog-fine-grained-or-not | 89.9% |
| dual-cross-attention-learning-for-fine | 92.0% |
| attribute-aware-attention-model-for-fine | 86.2% |
| sim-ofe-structure-information-mining-and | 92.3% |
| sr-gnn-spatial-relation-aware-graph-neural | 91.9% |
| learning-to-navigate-for-fine-grained | 87.5% |
| classification-specific-parts-for-improving | 89.5% |
| progressive-co-attention-network-for-fine | 88.9% |
| cross-x-learning-for-fine-grained-visual | 87.7% |
| deformable-part-descriptors-for-fine-grained | 50.98% |
| grad-cam-guided-channel-spatial-attention | 88.45% |
| knowledge-transfer-based-fine-grained-visual | 89.1% |
| transformer-with-peak-suppression-and | 91.3% |
| fine-grained-visual-classification-with | 88.9% |
| attention-convolutional-binary-neural-tree | 88.1% |
| part-guided-relational-transformers-for-fine | 90.1% |
| aligned-to-the-object-not-to-the-image-a | 89.2% |
| contrastively-reinforced-attention | 88.3% |
| fine-grained-classification-via-categorical | 88.2% |
| universal-fine-grained-visual-categorization | 92.6% |
| feature-fusion-vision-transformer-fine | 91.6% |
| graph-based-high-order-relation-discovery-for | 89.6% |
| a-free-lunch-from-vit-adaptive-attention | 91.5% |
| part-based-r-cnns-for-fine-grained-category | 76.4% |
| the-devil-is-in-the-channels-mutual-channel | 87.3% |
| end-to-end-learning-of-a-fisher-vector | 90.95% |
| bilinear-cnn-models-for-fine-grained-visual | 85.1% |
| metaformer-a-unified-meta-framework-for-fine | 92.9% |
| towards-faster-training-of-global-covariance | 88.7% |
| advisingnets-learning-to-distinguish-correct | 88.59% |
| multi-granularity-part-sampling-attention-for | 92.8% |
| fine-grained-representation-learning-and | 88.1% |
| selective-sparse-sampling-for-fine-grained | 88.5% |
| context-semantic-quality-awareness-network | 92.6% |
| the-unreasonable-effectiveness-of-noisy-data | 92.3% |
| interweaving-insights-high-order-feature | 91.6% |
| part-stacked-cnn-for-fine-grained-visual | 76.6% |
| rams-trans-recurrent-attention-multi-scale | 91.3% |
| large-scale-fine-grained-categorization-and | 89.6% |
| fine-grained-recognition-accounting-for | 88.6% |
| a-novel-plug-in-module-for-fine-grained-1 | 92.8% |
| pairwise-confusion-for-fine-grained-visual | 86.87% |
| delving-into-multimodal-prompting-for-fine | 91.8% |
| re-rank-coarse-classification-with-local | 91.1% |
| an-attention-locating-algorithm-for | 91.7% |
| penalizing-the-hard-example-but-not-too-much | 89.8% |
| alignment-enhancement-network-for-fine | 90.0% |
| vit-net-interpretable-vision-transformers | 91.7% |
| fine-grained-visual-classification-via-2 | 91.8% |
| fine-grained-visual-classification-using-self | 91.8% |
| fine-grained-visual-classification-via | 89.6% |
| the-devil-is-in-the-channels-mutual-channel | 86.4% |
| elope-fine-grained-visual-classification-with | 88.5% |