List your company
ResearchFormerly WizWand

Image Classification on Stylized ImageNet (SIN)

-49.45SIN GapUniform Soup
-73.9836-67.6143-61.245-54.8757Dec 9, 2022
Updated 8mo ago

Evaluation results

MethodLinks
Uniform SoupBackbone=ViT-B/32, Evaluation Protocol=Fine-tuned, Pre-training Dataset=WIT2022.12-49.45
MAE+LLEtrain data=IN-1k, evaluation protocol=Last Layer Ensemble, backbone=ViT-H2022.12-55.69
MAE+LLEBackbone=ViT-L/16, Evaluation Protocol=Fine-tuned2022.12-56.32
CLIPBackbone=ViT-L/16, Evaluation Protocol=Zero-shot, Pre-training Dataset=LAION2022.12-56.85
ERMBackbone=ViT-B/322022.12-57.16
Greedy SoupBackbone=ViT-B/32, Evaluation Protocol=Fine-tuned, Pre-training Dataset=WIT2022.12-57.51
MAE+LLEBackbone=ViT-B/16, Evaluation Protocol=Fine-tuned2022.12-58.78
CLIPtrain data=LAION-2B, evaluation protocol=zero-shot, backbone=ViT-H2022.12-59.47
SWAGtrain data=IG-3.6B, evaluation protocol=linear probing, backbone=ViT-H2022.12-59.99
SWAGBackbone=ViT-L/16, Evaluation Protocol=Linear Probing, Pre-training Dataset=IG-3.6B2022.12-60.26
CLIPBackbone=ViT-L/16, Evaluation Protocol=Zero-shot, Pre-training Dataset=WIT2022.12-61.27
ERMBackbone=ViT-L/162022.12-61.43
SWAGtrain data=IG-3.6B, evaluation protocol=fine-tuning, backbone=ViT-H2022.12-62.22
MAEtrain data=IN-1k, evaluation protocol=fine-tuning, backbone=ViT-H2022.12-62.29
MAEBackbone=ViT-L/16, Evaluation Protocol=Fine-tuned2022.12-62.48
ERMBackbone=ViT-B/162022.12-62.6
MoCov3Backbone=ViT-B/16, Evaluation Protocol=Linear Probing2022.12-63.36
SWAGBackbone=ViT-L/16, Evaluation Protocol=Fine-tuned, Pre-training Dataset=IG-3.6B2022.12-63.45
MAEBackbone=ViT-B/16, Evaluation Protocol=Fine-tuned2022.12-65.2
SWAGBackbone=ViT-B/16, Evaluation Protocol=Fine-tuned, Pre-training Dataset=IG-3.6B2022.12-66.99
SWAGBackbone=ViT-B/16, Evaluation Protocol=Linear Probing, Pre-training Dataset=IG-3.6B2022.12-67.33
ERMBackbone=RG-32gf2022.12-69.27
SEERBackbone=RG-32gf, Evaluation Protocol=Fine-tuned, Pre-training Dataset=IG-1B2022.12-73.04