HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Data Augmentation On Imagenet

Metrics

Accuracy (%)

Results

Performance results of various models on this benchmark

Model Name
Accuracy (%)
Paper TitleRepository
DeiT-S (+MixPro)81.3MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer-
ResNet-50 (LoRot-I)77.71Tailoring Self-Supervision for Supervised Learning-
DeiT-T (+MixPro)73.8MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer-
ResNet-50 (UA)77.63UniformAugment: A Search-free Probabilistic Data Augmentation Approach-
ResNet-200 (DeepAA)81.32Deep AutoAugment-
ResNet-200 (UA)80.4UniformAugment: A Search-free Probabilistic Data Augmentation Approach-
DeiT-B (+MixPro)82.9MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer-
ResNet-50 (RA)77.6RandAugment: Practical automated data augmentation with a reduced search space-
ResNet-200 (AA)80.0AutoAugment: Learning Augmentation Policies from Data-
ResNet-50 (DeepAA)78.30Deep AutoAugment-
ResNet-50 (AA)77.6AutoAugment: Learning Augmentation Policies from Data-
ResNet-50 (Faster AA)76.5Faster AutoAugment: Learning Augmentation Strategies using Backpropagation-
ResNet-50 (Fast AA)77.6Fast AutoAugment-
ResNet-200 (Fast AA)80.6Fast AutoAugment-
ResNet-50 (TA wide)78.07TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation-
ResNet-50 (LoRot-E)77.72Tailoring Self-Supervision for Supervised Learning-
ResNet-50 (DADA)77.5DADA: Differentiable Automatic Data Augmentation-
0 of 17 row(s) selected.
Data Augmentation On Imagenet | SOTA | HyperAI