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 Objectnet

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
ResNet-50 + MixUp (rescaled)28.37On Mixup Regularization
MoCo-v2 (BG_Swaps)20.8Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations-
AR-B (Opt Relevance)47.1Optimizing Relevance Maps of Vision Transformers Improves Robustness
RegViT (RandAug)29.3Pyramid Adversarial Training Improves ViT Performance
Vit B/16 (Bamboo)53.9Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
CLIP (CC12M pretrain)15.24Robust Cross-Modal Representation Learning with Progressive Self-Distillation-
MLP-Mixer + Pixel24.75Pyramid Adversarial Training Improves ViT Performance
ALIGN72.2Combined Scaling for Zero-shot Transfer Learning-
RegNetY 128GF (Platt)64.3Revisiting Weakly Supervised Pre-Training of Visual Perception Models
ViT H/14 (Platt)60Revisiting Weakly Supervised Pre-Training of Visual Perception Models
NASNet-A35.77ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models-
SWAG (ViT H/14)69.5Revisiting Weakly Supervised Pre-Training of Visual Perception Models
SwAV (reverse linear probing)17.71Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing-
BYOL (BG_RM)23.9Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations-
Inception-v432.24ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models-
AlexNet6.78ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models-
Discrete ViT29.95Pyramid Adversarial Training Improves ViT Performance
SwAV (BG_RM)21.9Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations-
MAWS (ViT-H)72.6The effectiveness of MAE pre-pretraining for billion-scale pretraining
OBoW (reverse linear probing)12.23Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing-
0 of 106 row(s) selected.