HyperAIHyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAIHyperAI超神経

Image Classification On Imagenet Real

評価指標

Accuracy
Params

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Accuracy
Params
Paper TitleRepository
BiT-L90.54%928MBig Transfer (BiT): General Visual Representation Learning-
MAWS (ViT-6.5B)91.1%-The effectiveness of MAE pre-pretraining for billion-scale pretraining-
ResMLP-3685.6%45MResMLP: Feedforward networks for image classification with data-efficient training-
Assemble ResNet-5087.82%-Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network-
ResMLP-B24/8 (22k)--ResMLP: Feedforward networks for image classification with data-efficient training-
BiT-M89.02%-Big Transfer (BiT): General Visual Representation Learning-
Model soups (ViT-G/14)91.20%1843MModel soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time-
CeiT-T83.6%-Incorporating Convolution Designs into Visual Transformers-
TokenLearner L/8 (24+11)91.05%460MTokenLearner: What Can 8 Learned Tokens Do for Images and Videos?-
Meta Pseudo Labels (EfficientNet-L2)91.02%-Meta Pseudo Labels-
ViTAE-H (MAE, 512)91.2%644MViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond-
Model soups (BASIC-L)91.03%2440MModel soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time-
FixResNeXt-101 32x48d89.73%829MFixing the train-test resolution discrepancy-
LeViT-38487.5%-LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference-
ViT-L @384 (DeiT III, 21k)--DeiT III: Revenge of the ViT-
VOLO-D590.6%-VOLO: Vision Outlooker for Visual Recognition-
ResMLP-1284.6%15MResMLP: Feedforward networks for image classification with data-efficient training-
NASNet-A Large87.56%-Learning Transferable Architectures for Scalable Image Recognition-
Assemble-ResNet15288.65%-Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network-
DeiT-Ti82.1%5MTraining data-efficient image transformers & distillation through attention-
0 of 57 row(s) selected.