Image Classification On Flowers 102

评估指标

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	Accuracy	Paper Title	Repository
Mixer-S/16- SAM	87.9	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
CeiT-S (384 finetune resolution)	98.6	Incorporating Convolution Designs into Visual Transformers
NAT-M1	-	Neural Architecture Transfer
CeiT-T	96.9	Incorporating Convolution Designs into Visual Transformers
ResNet-152-SAM	91.1	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
ResMLP12	97.4	ResMLP: Feedforward networks for image classification with data-efficient training
VIT-L/16 (Background)	99.75	Reduction of Class Activation Uncertainty with Background Information
NAT-M3	98.1%	Neural Architecture Transfer
NNCLR	95.1	With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
Bamboo (ViT-B/16)	99.7	Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
ResMLP24	97.9	ResMLP: Feedforward networks for image classification with data-efficient training
CeiT-T (384 finetune resolution)	97.8	Incorporating Convolution Designs into Visual Transformers
ResNet-50x1-ACG (ImageNet-21K)	98.21	Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images
CCT-14/7x2	99.76	Escaping the Big Data Paradigm with Compact Transformers
CaiT-M-36 U 224	99.1	Going deeper with Image Transformers
DAT	98.9%	Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization	-
SEER (RegNet10B)	96.3	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
ResNet-152x4-AGC (ImageNet-21K)	99.49	Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images
CeiT-S	98.2	Incorporating Convolution Designs into Visual Transformers
TransBoost-ResNet50	97.85%	TransBoost: Improving the Best ImageNet Performance using Deep Transduction

0 of 51 row(s) selected.