Image Classification on RESISC45

Metric: Top 1 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Top 1 Accuracy▼	Extra Data	Paper	Date↕	Code
1	ResNet50	96.83	Yes	In-domain representation learning for remote sen...	2019-11-15	Code
2	LWGANet L2	96.17	No	LWGANet: A Lightweight Group Attention Backbone ...	2025-01-17	Code
3	DecoupleNet D2	95.87	No	-	-	Code
4	LWGANet L1	95.7	No	LWGANet: A Lightweight Group Attention Backbone ...	2025-01-17	Code
5	SEER (RegNet10B)	95.61	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
6	LWGANet L0	95.49	No	LWGANet: A Lightweight Group Attention Backbone ...	2025-01-17	Code
7	AGOS	94.91	No	All Grains, One Scheme (AGOS): Learning Multi-gr...	2022-05-06	Code
8	SwAV (ResNet50-w5)	94.73	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
9	DINO (DeiT-B/16)	93.97	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
10	LSENet	93.49	No	-	-	Code
11	MoCo-v3 (ViT-B/16)	93.35	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
12	CLIP (ViT-B/16)	92.7	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
13	BYOL (ResNet200-w2)	92.53	Yes	-	-	-
14	DeiT-B/16	92.48	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
15	SimCLR-v2 (ResNet152-w3 + SK)	89.77	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
16	ResNet50 (ImageNet-supervised)	88.56	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
17	MIDC-Net	87.99	No	-	-	Code
18	MoCo-v2 (ResNet50)	85.4	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code

#1ResNet50SOTA
96.83
Top 1 Accuracy· Extra Data· 2019-11-15
In-domain representation learning for remote sensing Code
#2LWGANet L2
96.17
Top 1 Accuracy· 2025-01-17
LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks Code
#3DecoupleNet D2
95.87
Top 1 Accuracy
No paperCode
#4LWGANet L1
95.7
Top 1 Accuracy· 2025-01-17
LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks Code
#5SEER (RegNet10B)
95.61
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#6LWGANet L0
95.49
Top 1 Accuracy· 2025-01-17
LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks Code
#7AGOS
94.91
Top 1 Accuracy· 2022-05-06
All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification Code
#8SwAV (ResNet50-w5)
94.73
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#9DINO (DeiT-B/16)
93.97
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#10LSENet
93.49
Top 1 Accuracy
No paperCode
#11MoCo-v3 (ViT-B/16)
93.35
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#12CLIP (ViT-B/16)
92.7
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#13BYOL (ResNet200-w2)
92.53
Top 1 Accuracy· Extra Data
No paper
#14DeiT-B/16
92.48
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#15SimCLR-v2 (ResNet152-w3 + SK)
89.77
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#16ResNet50 (ImageNet-supervised)
88.56
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#17MIDC-Net
87.99
Top 1 Accuracy
No paperCode
#18MoCo-v2 (ResNet50)
85.4
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code