Learning With Noisy Labels On Animal
评估指标
Accuracy
ImageNet Pretrained
Network
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Accuracy | ImageNet Pretrained | Network |
|---|---|---|---|
| jigsaw-vit-learning-jigsaw-puzzles-in-vision | 89.0 | NO | DeiT-S |
| learning-with-feature-dependent-label-noise-a-1 | 79.4 | NO | Vgg19-BN |
| boosting-co-teaching-with-compression | 81.3 | NO | Vgg19-BN |
| learning-with-feature-dependent-label-noise-a-1 | 83.4 | NO | Vgg19-BN |
| cross-to-merge-training-with-class-balance | 85.9 | NO | Vgg-19-BN |
| boosting-co-teaching-with-compression | 81.3 | NO | Vgg19-BN |
| sure-survey-recipes-for-building-reliable-and | 89.0 | NO | Vgg19-BN |
| selfie-refurbishing-unclean-samples-for | 81.8 | NO | Vgg19-BN |
| psscl-a-progressive-sample-selection | 88.74 | NO | Vgg19-BN |
| dynamic-loss-for-robust-learning | 86.5 | NO | Vgg19-BN |
| instance-dependent-noisy-label-learning-via | 84.6 | NO | Vgg19-BN |
| s3-supervised-self-supervised-learning-under-1 | 88.5 | NO | Vgg19-BN |
| instance-dependent-noisy-label-learning-via | 84.7 | NO | ConvNeXt |
| compressing-features-for-learning-with-noisy | 84.1 | NO | Vgg19-BN |
| bootstrapping-the-relationship-between-images | 88.5 | NO | Vgg19-BN |
| scalable-penalized-regression-for-noise | 86.8 | NO | VGG19-BN |
| generative-noisy-label-learning-by-implicit | 85.9 | NO | Vgg-19-BN |
| instance-dependent-noisy-label-learning-via | 82.3 | NO | ResNet |