List your company
ResearchFormerly WizWand

Image Classification on RESISC

97.1AccuracyCLIP* L/14
7.836831.010954.18577.3591Jun 13, 2023Dec 8, 2023Jun 4, 2024Nov 30, 2024May 28, 2025Nov 23, 2025May 21, 2026
Updated 5mo ago

Evaluation results

MethodLinks
CLIP* L/14MAP head=true, Grain=Coarse, Frozen representation=true, backbone=ViT-L/142023.0697.1
CapPa L/14MAP head=true, Grain=Coarse, Frozen representation=true, backbone=ViT-L/142023.0696.9
CLIP* (16k)MAP head=true, Grain=Coarse, Frozen representation=true2023.0696.4
CapPaMAP head=true, Grain=Coarse, Frozen representation=true2023.0696.1
Fine-TunedBackbone=DINOv3 ViT-B/162025.1295.7
Linear ProbeBackbone=DINOv3 ViT-B/162025.1292.7
CLIP* (8k)MAP head=true, Grain=Coarse, Frozen representation=true2023.0692.5
Fine-TunedBackbone=CLIP ViT-B/32, Classes=452025.1292.3
Linear ProbeBackbone=CLIP ViT-B/32, Classes=452025.1291.7
Task MatrixBackbone=DINOv3 ViT-B/16, best layer=112025.1291.4
CapMAP head=true, Grain=Coarse, Frozen representation=true2023.0690.5
Task MatrixBackbone=CLIP ViT-B/32, Best Layer=11, Classes=452025.1289.1
CLIP ViT-B/16Img. encoder=CLIP ViT-B/162026.0557.14
CLIP ViT-B/32Img. encoder=CLIP ViT-B/322026.0555.19
CLIP RN-101Img. encoder=CLIP RN-1012026.0541.37
CLIP RN-50Img. encoder=CLIP RN-502026.0541.25
TinyViT-21M + CLIPImg. encoder=TinyViT-21M, Txt. encoder=CLIP2026.0528.33
ConvNext-B + CLIPImg. encoder=ConvNext-B, Txt. encoder=CLIP2026.0527.29
ConvNext-B + MPNetImg. encoder=ConvNext-B, Txt. encoder=MPNet2026.0524.65
TinyViT-21M + MPNetImg. encoder=TinyViT-21M, Txt. encoder=MPNet2026.0524.59
BEiT-B/16 + CLIPImg. encoder=BEiT-B/16, Txt. encoder=CLIP2026.0524.21
ConvNext-B + RoBERTaImg. encoder=ConvNext-B, Txt. encoder=RoBERTa2026.0522.79
TinyViT-21M + RoBERTaImg. encoder=TinyViT-21M, Txt. encoder=RoBERTa2026.0522.75
ConvNext-B + MiniLMImg. encoder=ConvNext-B, Txt. encoder=MiniLM2026.0521.73
BEiT-B/16 + MPNetImg. encoder=BEiT-B/16, Txt. encoder=MPNet2026.0520.95
ConvFormer-S18 + CLIPImg. encoder=ConvFormer-S18, Txt. encoder=CLIP2026.0519.71
TinyViT-21M + MiniLMImg. encoder=TinyViT-21M, Txt. encoder=MiniLM2026.0518.68
BEiT-B/16 + RoBERTaImg. encoder=BEiT-B/16, Txt. encoder=RoBERTa2026.0518.54
CAFormer-S18 + MPNetImg. encoder=CAFormer-S18, Txt. encoder=MPNet2026.0518.52
ConvFormer-S18 + MPNetImg. encoder=ConvFormer-S18, Txt. encoder=MPNet2026.0518.52
ConvFormer-S18 + RoBERTaImg. encoder=ConvFormer-S18, Txt. encoder=RoBERTa2026.0517.33
CAFormer-S18 + CLIPImg. encoder=CAFormer-S18, Txt. encoder=CLIP2026.0516.89
CAFormer-S18 + RoBERTaImg. encoder=CAFormer-S18, Txt. encoder=RoBERTa2026.0516.11
BEiT-B/16 + MiniLMImg. encoder=BEiT-B/16, Txt. encoder=MiniLM2026.0514.35
ConvFormer-S18 + MiniLMImg. encoder=ConvFormer-S18, Txt. encoder=MiniLM2026.0512.73
CAFormer-S18 + MiniLMImg. encoder=CAFormer-S18, Txt. encoder=MiniLM2026.0511.27