HyperAIHyperAI
StartseiteNeuigkeitenNeueste ForschungsarbeitenTutorialsDatensätzeWikiSOTALLM-ModelleGPU-RanglisteVeranstaltungen
Suche
Über
HyperAIHyperAI

Unsupervised Domain Adaptation On Imagenet C

Metriken

mean Corruption Error (mCE)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
mean Corruption Error (mCE)
Paper TitleRepository
ResNeXt101 32x8d + DeepAug + Augmix + RPL34.8If your data distribution shifts, use self-learning-
EfficientNet-L2+ENT23.0If your data distribution shifts, use self-learning-
ResNeXt101 32x8d + IG-3.5B + RPL40.9If your data distribution shifts, use self-learning-
ResNet50 + RPL50.5If your data distribution shifts, use self-learning-
ResNeXt101 32x8d + RPL43.2If your data distribution shifts, use self-learning-
ResNet50 + ENT51.6If your data distribution shifts, use self-learning-
ResNeXt101 32x8d + ENT44.3If your data distribution shifts, use self-learning-
ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, full adaptation38.0Improving robustness against common corruptions by covariate shift adaptation-
ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, 8 samples40.7Improving robustness against common corruptions by covariate shift adaptation-
ResNeXt101 32x8d + DeepAug + Augmix + ENT35.5If your data distribution shifts, use self-learning-
ResNet50+DeepAug+AugMix, BatchNorm Adaptation, 8 samples48.4Improving robustness against common corruptions by covariate shift adaptation-
ResNet50 (baseline), BatchNorm Adaptation, 8 samples65.0Improving robustness against common corruptions by covariate shift adaptation-
ResNet50 (baseline), BatchNorm Adaptation, full adaptation62.2Improving robustness against common corruptions by covariate shift adaptation-
ResNet50+DeepAug+AugMix, BatchNorm Adaptation, full adaptation45.4Improving robustness against common corruptions by covariate shift adaptation-
ResNeXt101 32x8d + IG-3.5B + ENT40.8If your data distribution shifts, use self-learning-
EfficientNet-L2+RPL22.0If your data distribution shifts, use self-learning-
0 of 16 row(s) selected.
Unsupervised Domain Adaptation On Imagenet C | SOTA | HyperAI