Fine Grained Image Classification On Nabirds
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| align-yourself-self-supervised-pre-training | 79.64% |
| learning-attentive-pairwise-interaction-for | 88.1% |
| interweaving-insights-high-order-feature | 92.12% |
| transformer-with-peak-suppression-and | 90.1% |
| a-novel-plug-in-module-for-fine-grained-1 | 92.8% |
| multi-granularity-part-sampling-attention-for | 92.5% |
| fine-grained-visual-classification-with-high-1 | 93.0% |
| transfg-a-transformer-architecture-for-fine | 90.8% |
| universal-fine-grained-visual-categorization | 91.7% |
| end-to-end-learning-of-a-fisher-vector | 90.3% |
| aligned-to-the-object-not-to-the-image-a | 87.9% |
| classification-specific-parts-for-improving | 88.5% |
| delving-into-multimodal-prompting-for-fine | 91.0% |
| maximum-entropy-fine-grained-classification | 83.0% |
| fixing-the-train-test-resolution-discrepancy | 89.2% |
| an-attention-locating-algorithm-for | 91.1% |
| classification-specific-parts-for-improving | 88.5% |
| metaformer-a-unified-meta-framework-for-fine | 93.0% |
| bilinear-cnns-for-fine-grained-visual | 79.4% |
| pairwise-confusion-for-fine-grained-visual | 82.79% |
| fine-grained-visual-classification-via-2 | 90.8% |
| transifc-invariant-cues-aware-feature | 90.9% |
| cross-x-learning-for-fine-grained-visual | 86.4% |
| learning-a-mixture-of-granularity-specific | 88.6% |
| sr-gnn-spatial-relation-aware-graph-neural | 91.2% |
| context-semantic-quality-awareness-network | 92.3% |
| context-aware-attentional-pooling-cap-for | 91.0% |