Image Classification on Flowers-102

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	CCT-14/7x2	99.76	Yes	Escaping the Big Data Paradigm with Compact Tran...	2021-04-12	Code
2	VIT-L/16 (Background)	99.75	Yes	Reduction of Class Activation Uncertainty with B...	2023-05-05	Code
3	CvT-W24	99.72	Yes	CvT: Introducing Convolutions to Vision Transfor...	2021-03-29	Code
4	Bamboo (ViT-B/16)	99.7	Yes	Bamboo: Building Mega-Scale Vision Dataset Conti...	2022-03-15	Code
5		99.68	No	An Image is Worth 16x16 Words: Transformers for ...	2020-10-22	Code
6	BiT-L (ResNet)	99.63	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
7	ConvMLP-S	99.5	Yes	ConvMLP: Hierarchical Convolutional MLPs for Vis...	2021-09-09	Code
8	ConvMLP-L	99.5	Yes	ConvMLP: Hierarchical Convolutional MLPs for Vis...	2021-09-09	Code
9	ResNet-152x4-AGC (ImageNet-21K)	99.49	Yes	Effect of Pre-Training Scale on Intra- and Inter...	2021-05-31	Code
10	BiT-M (ResNet)	99.3	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
11	Wide-ResNet-101 (Spinal FC)	99.3	Yes	SpinalNet: Deep Neural Network with Gradual Input	2020-07-07	Code
12	CaiT-M-36 U 224	99.1	Yes	Going deeper with Image Transformers	2021-03-31	Code
13	EfficientNetV2-L	98.8	Yes	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
14	GFNet-H-B	98.8	Yes	Global Filter Networks for Image Classification	2021-07-01	Code
15	CeiT-S (384 finetune resolution)	98.6	Yes	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
16	EfficientNetV2-M	98.5	Yes	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
17	ViT-B (attn finetune)	98.5	Yes	Three things everyone should know about Vision T...	2022-03-18	Code
18	LeViT-384	98.3	Yes	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
19	ResNet-50x1-ACG (ImageNet-21K)	98.21	Yes	Effect of Pre-Training Scale on Intra- and Inter...	2021-05-31	Code
20	CeiT-S	98.2	Yes	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
21	ResNet50 (A1)	97.9	Yes	ResNet strikes back: An improved training proced...	2021-10-01	Code
22	EfficientNetV2-S	97.9	Yes	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
23	ResMLP24	97.9	Yes	ResMLP: Feedforward networks for image classific...	2021-05-07	Code
24	CeiT-T (384 finetune resolution)	97.8	Yes	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
25	LeViT-192	97.8	Yes	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
26	LeViT-256	97.7	Yes	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
27	ResMLP12	97.4	Yes	ResMLP: Feedforward networks for image classific...	2021-05-07	Code
28	CeiT-T	96.9	Yes	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
29	LeViT-128S	96.8	Yes	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
30	SEER (RegNet10B)	96.3	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
31	NNCLR	95.1	Yes	With a Little Help from My Friends: Nearest-Neig...	2021-04-29	Code
32	ViT-B/16- SAM	91.8	Yes	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
33	ViT-S/16- SAM	91.5	Yes	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
34	ResNet-152-SAM	91.1	Yes	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
35	ResNet-50-SAM	90	Yes	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
36	Mixer-B/16- SAM	90	Yes	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
37	MANO-tiny	89	Yes	Linear Attention with Global Context: A Multipol...	2025-07-03	Code
38	Mixer-S/16- SAM	87.9	Yes	When Vision Transformers Outperform ResNets with...	2021-06-03	Code