List your company
ResearchFormerly WizWand

Image Classification on AID

96.6AccuracySOTA
19.53639.54359.5579.557May 23, 2023Nov 25, 2023May 30, 2024Dec 2, 2024Jun 7, 2025Dec 10, 2025Jun 15, 2026
Updated 4mo ago

Evaluation results

MethodLinks
SOTASetting=Transductive, Transductive Inference (TransCLIP)=false2025.0696.6
T-RemoteCLIPSetting=Transductive, Transductive Inference (TransCLIP)=true2025.0695.6
DINOv2-LVD142MBackbone=ViT-L/14, Training Scale=large scale datasets, Evaluation protocol=Linear probe2026.0694.27
Earth-Agent2025.0993.42
S-CLIPModel=ViT-B/162023.0593.1
VISReg-Inet22KBackbone=ViT-L/14, Training Scale=large scale datasets, Evaluation protocol=Linear probe2026.0692.81
S-CLIPModel=ViT-B/322023.0592.5
CLIPModel=ViT-B/32, Training Mode=fine-tune2023.0592
iBOTBackbone=ViT-B/16, Heuristics=Included, Evaluation protocol=Linear probe2026.0691.73
VHM2025.0991.7
RemoteCLIPSetting=Transductive, Transductive Inference (TransCLIP)=false2025.0691.7
DINOBackbone=ViT-B/16, Heuristics=Included, Evaluation protocol=Linear probe2026.0691.52
RemoteCLIPArchitecture=ViT-B/32, Setting=Zero-shot, Template=DST2026.0691.5
RemoteCLIPBackbone=ViT-B-32, zero-shot=true2023.0691.3
RemoteCLIPBackbone=ViT-B-32, zero-shot=true2023.0691.3
LHRS-Bot2025.0991.26
iBOTBackbone=ViT-L/16, Heuristics=Included, Evaluation protocol=Linear probe2026.0691.24
VISRegBackbone=ViT-B/16, Heuristics=Excluded, Evaluation protocol=Linear probe2026.0690.91
MoCoV3Backbone=ViT-B/16, Heuristics=Included, Evaluation protocol=Linear probe2026.0690.2
VISRegBackbone=ViT-L/14, Heuristics=Excluded, Evaluation protocol=Linear probe2026.0690.12
RemoteCLIPArchitecture=RN-50, Setting=Zero-shot, Template=DST2026.0689.4
CLIPModel=ViT-B/16, Training Mode=fine-tune2023.0589.2
EarthDialBackbone=Phi-3, zero-shot=true2025.1288.76
I-JEPABackbone=ViT-H/14, Heuristics=Included, Evaluation protocol=Linear probe2026.0688.68
GeoVLM-R1Backbone=Qwen2.5VL-3B, zero-shot=true2025.1288.46
RemoteCLIPBackbone=ViT-L-14, zero-shot=true2023.0687.9
RemoteCLIPBackbone=ViT-L-14, zero-shot=true2023.0687.9
S-CLIPModel=ResNet-502023.0587.7
GeoMELTBackbone=BEiT-3, zero-shot=true2025.1287.4
RemoteCLIPBackbone=ViT-B, zero-shot=true2025.1286.6
RemoteCLIPBackbone=ResNet-50, zero-shot=true2023.0686.55
RemoteCLIPBackbone=ResNet-50, zero-shot=true2023.0686.55
MAEBackbone=ViT-L/16, Heuristics=Excluded, Evaluation protocol=Linear probe2026.0686.42
data2vecBackbone=ViT-L/16, Heuristics=Included, Evaluation protocol=Linear probe2026.0685.98
SkyNativeParams.=8B2026.0584.83
RemoteCLIPArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.0684.2
CLIPModel=ResNet-50, Training Mode=fine-tune2023.0583.6
T-CLIPSetting=Transductive, Transductive Inference (TransCLIP)=true2025.0680.7
VHMParams.=7B2026.0579
MetaCLIP-2.5BArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.0678.9
T-SkyCLIP50Setting=Transductive, Transductive Inference (TransCLIP)=true2025.0678.7
T-GeoRSCLIPSetting=Transductive, Transductive Inference (TransCLIP)=true2025.0678.2
AVIONBackbone=GeoRSCLIP (ViT-B/32), Evaluation Protocol=Zero-shot2026.0377.99
RemoteCLIPBackbone=ViT-L, zero-shot=true2025.1276.95
GeoRSCLIPArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.0676.9
APPLeNetBackbone=GeoRSCLIP (ViT-B/32), Evaluation Protocol=Zero-shot2026.0376.4
Gemini-2.02026.0576
SkySenseGPTParams.=7B2026.0575.5
SigLIP2Architecture=ViT-L/16, Setting=Zero-shot, Template=DST2026.0674.7
MetaCLIP-400MArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.0673.9
GeoRSCLIPBackbone=GeoRSCLIP (ViT-B/32), Evaluation Protocol=Zero-shot2026.0373.72
SigLIP2Architecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.0672.7
MetaCLIP-2.5BArchitecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.0672.5
CLIP LAION-RSArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.0672.5
SigLIPArchitecture=ViT-L/16, Setting=Zero-shot, Template=DST2026.0672.2
SkyCLIPArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.0672.2
GeoRSCLIPArchitecture=ViT-B/32, Setting=Zero-shot, Template=DST2026.0672.1
GeoChatBackbone=LLaVA-1.5-7B, zero-shot=true2025.1272.03
Geochat2025.0972.03
MetaCLIP-400MArchitecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.0671.8
SigLIPArchitecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.0671
GeoRSCLIPSetting=Transductive, Transductive Inference (TransCLIP)=false2025.0670.3
SkyCLIP50Setting=Transductive, Transductive Inference (TransCLIP)=false2025.0670.3
CLIPBackbone=ViT-L-14, zero-shot=true2023.0669.88
CLIPBackbone=ViT-L-14, zero-shot=true2023.0669.88
CLIPArchitecture=ViT-L/14, Setting=Zero-shot, Template=DST2026.0669.4
Qwen2.5-VLParams.=7B2026.0568.17
EarthDialParams.=4B2026.0567.33
CLIPArchitecture=ViT-B/16, Setting=Zero-shot, Template=DST2026.0667.3
CLIPSetting=Transductive, Transductive Inference (TransCLIP)=false2025.0666.4
CLIPBackbone=ViT-B-32, zero-shot=true2023.0665.65
CLIPBackbone=ViT-B-32, zero-shot=true2023.0665.65
EVEv2Params.=7B2026.0564.17
CLIPBackbone=ViT-L, zero-shot=true2025.1262.7
Claude-42026.0560.33
Sphinx2025.0958.2
CLIPBackbone=ResNet-50, zero-shot=true2023.0657.35
CLIPBackbone=ResNet-50, zero-shot=true2023.0657.35
CLIPBackbone=ViT-B, zero-shot=true2025.1251.4
LLaVA-1.52025.0951
VoCoTParams.=7B2026.0546.67
MiniGPT-v22025.0932.96
MiniGPT-v2Params.=7B2026.0522.5