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

		Paper Title	Repository
CCT-14/7x2	99.76	Escaping the Big Data Paradigm with Compact Transformers
VIT-L/16 (Background)	99.75	Reduction of Class Activation Uncertainty with Background Information
CvT-W24	99.72	CvT: Introducing Convolutions to Vision Transformers
Bamboo (ViT-B/16)	99.7	Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
模型 36	99.68	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
EffNet-L2 (SAM)	99.65%	Sharpness-Aware Minimization for Efficiently Improving Generalization
ALIGN	99.65%	Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
BiT-L (ResNet)	99.63	Big Transfer (BiT): General Visual Representation Learning
ConvMLP-S	99.5	ConvMLP: Hierarchical Convolutional MLPs for Vision
ConvMLP-L	99.5	ConvMLP: Hierarchical Convolutional MLPs for Vision
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
Wide-ResNet-101 (Spinal FC)	99.30	SpinalNet: Deep Neural Network with Gradual Input
BiT-M (ResNet)	99.30	Big Transfer (BiT): General Visual Representation Learning
CaiT-M-36 U 224	99.1	-	-
Grafit (RegNet-8GF)	99.1%	Grafit: Learning fine-grained image representations with coarse labels	-
TResNet-L	99.1%	TResNet: High Performance GPU-Dedicated Architecture
DAT	98.9%	Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization	-
GFNet-H-B	98.8	Global Filter Networks for Image Classification
EfficientNet-B7	98.8%	EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
DeiT-B	98.8%	Training data-efficient image transformers & distillation through attention

0 of 51 row(s) selected.