Image Classification On Webvision 1000
Metriken
ImageNet Top-1 Accuracy
ImageNet Top-5 Accuracy
Top-1 Accuracy
Top-5 Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | ImageNet Top-1 Accuracy | ImageNet Top-5 Accuracy | Top-1 Accuracy | Top-5 Accuracy |
|---|---|---|---|---|
| webly-supervised-image-classification-with-1 | 69.42% | 87.29% | 75.48% | 90.15% |
| protonet-learning-from-web-data-with-memory | 65.0% | 85.1% | 72.2% | 89.5% |
| heteroskedastic-and-imbalanced-deep-learning | 67.1% | 86.7% | 75.0% | 90.6% |
| mopro-webly-supervised-learning-with-momentum | 67.8% | 87.0% | 73.9% | 90.0% |
| improving-image-recognition-by-retrieving | - | - | 83.6 | - |
| learning-with-neighbor-consistency-for-noisy-1 | - | - | 75.7% | - |
| curriculumnet-weakly-supervised-learning-from | 64.8% | 84.9% | 72.1% | 89.2% |
| mentornet-learning-data-driven-curriculum-for | 62.5% | 83.0% | 70.8% | 88.0% |
| multi-label-iterated-learning-for-image | 67.1 | 85.6 | 75.2% | 90.3% |
| synthetic-vs-real-deep-learning-on-controlled-1 | 67.5% | 87.2% | 74.3% | 90.5% |
| curriculumnet-weakly-supervised-learning-from | - | - | 79.3% | 93.6% |
| multi-label-iterated-learning-for-image | 68.7 | 86.4 | 76.5% | 90.9% |
| learning-with-neighbor-consistency-for-noisy-1 | - | - | 76.8 | - |
| correlated-input-dependent-label-noise-in | - | - | 76.6% | 92.1% |
| cmw-net-learning-a-class-aware-sample | - | - | 77.9% | 92.6% |
| webly-supervised-image-classification-with | 70.66% | 88.46% | 75.78% | 91.07% |