Image Classification On Cifar 10

评估指标

Percentage correct

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
DINOv2 (ViT-g/14, frozen model, linear eval)	99.5	DINOv2: Learning Robust Visual Features without Supervision
ViT-H/14	99.5	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
µ2Net (ViT-L/16)	99.49	An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
ViT-L/16	99.42	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
CaiT-M-36 U 224	99.4	-	-
CvT-W24	99.39	CvT: Introducing Convolutions to Vision Transformers
BiT-L (ResNet)	99.37	Big Transfer (BiT): General Visual Representation Learning
RDNet-L (224 res, IN-1K pretrained)	99.31	DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
RDNet-B (224 res, IN-1K pretrained)	99.31	DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
ViT-B (attn fine-tune)	99.3	Three things everyone should know about Vision Transformers
Heinsen Routing + BEiT-large 16 224	99.2	An Algorithm for Routing Vectors in Sequences
ViT-B/16 (PUGD)	99.13	Perturbated Gradients Updating within Unit Space for Deep Learning
Astroformer	99.12	Astroformer: More Data Might not be all you need for Classification
CeiT-S (384 finetune resolution)	99.1	Incorporating Convolution Designs into Visual Transformers
TNT-B	99.1	Transformer in Transformer
DeiT-B	99.1	Training data-efficient image transformers & distillation through attention
EfficientNetV2-L	99.1	EfficientNetV2: Smaller Models and Faster Training
AutoFormer-S \| 384	99.1	AutoFormer: Searching Transformers for Visual Recognition
VIT-L/16 (Spinal FC, Background)	99.05	Reduction of Class Activation Uncertainty with Background Information
LaNet	99.03	Sample-Efficient Neural Architecture Search by Learning Action Space for Monte Carlo Tree Search	-

0 of 264 row(s) selected.