HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Domain Generalization On Imagenet Sketch

Metrics

Top-1 accuracy

Results

Performance results of various models on this benchmark

Paper Title
Model soups (BASIC-L)77.18Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Model soups (ViT-G/14)74.24Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
CAR-FT (CLIP, ViT-L/14@336px)65.5Context-Aware Robust Fine-Tuning
ConvNeXt-XL (Im21k, 384)55.0A ConvNet for the 2020s
CAFormer-B36 (IN21K, 384)54.5MetaFormer Baselines for Vision
LLE (ViT-H/14, MAE, Edge Aug)53.39A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
ConvFormer-B36 (IN21K, 384)52.9MetaFormer Baselines for Vision
CAFormer-B36 (IN21K)52.8MetaFormer Baselines for Vision
ConvFormer-B36 (IN21K)52.7MetaFormer Baselines for Vision
MAE (ViT-H, 448)50.9Masked Autoencoders Are Scalable Vision Learners
MAE+DAT (ViT-H)50.03Enhance the Visual Representation via Discrete Adversarial Training
GPaCo (ViT-L)48.3Generalized Parametric Contrastive Learning
Discrete Adversarial Distillation (ViT-B, 224)46.1Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models
Pyramid Adversarial Training Improves ViT (Im21k)46.03Pyramid Adversarial Training Improves ViT Performance
SEER (RegNet10B)45.6Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
DrViT44.72Discrete Representations Strengthen Vision Transformer Robustness
CAFormer-B3642.5MetaFormer Baselines for Vision
Pyramid Adversarial Training Improves ViT41.04Pyramid Adversarial Training Improves ViT Performance
ConvFormer-B3639.5MetaFormer Baselines for Vision
Sequencer2D-L35.8Sequencer: Deep LSTM for Image Classification
0 of 20 row(s) selected.