HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Image Classification On Inaturalist

评估指标

Top 1 Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称
Top 1 Accuracy
Paper TitleRepository
MetaSAug63.28%MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
AIMv2-1B79.7Multimodal Autoregressive Pre-training of Large Vision Encoders
SpineNet-14363.6%SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
iSQRT-COV-Net-Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
MAE (ViT-H, 448)83.4Masked Autoencoders Are Scalable Vision Learners
b_22DeiT-LT(ours)-DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
AIMv2-H77.9Multimodal Autoregressive Pre-training of Large Vision Encoders
Hiera-H (448px)83.8Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
FixSENet-15475.4Fixing the train-test resolution discrepancy
IncResNetV2 SE67.3%The iNaturalist Species Classification and Detection Dataset
MetaFormer (MetaFormer-2,384,extra_info)83.4%MetaFormer: A Unified Meta Framework for Fine-Grained Recognition
MetaFormer (MetaFormer-2,384)80.4%MetaFormer: A Unified Meta Framework for Fine-Grained Recognition
TransFG71.7TransFG: A Transformer Architecture for Fine-grained Recognition
Graph-RISE (40M)31.12%Graph-RISE: Graph-Regularized Image Semantic Embedding
SEB+EfficientNet-B572.3On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
AIMv2-3B81.5Multimodal Autoregressive Pre-training of Large Vision Encoders
AIMv2-L76Multimodal Autoregressive Pre-training of Large Vision Encoders
AIMv2-3B (448 res)85.9Multimodal Autoregressive Pre-training of Large Vision Encoders
0 of 18 row(s) selected.