List your company

Image-Text Retrieval on RSICD (test)

10.43mRVSE++
9.602415.188720.77526.3613Aug 24, 2023Sep 1, 2023Sep 9, 2023Sep 17, 2023Sep 25, 2023Oct 3, 2023Oct 12, 2023

Evaluation results

MethodLinks
VSE++Backbone=ResNet18, GRU, Params=15.78M2023.0810.43
CAMP-bceBackbone=Faster R-CNN, biGRU, Params=27.03M2023.0811.38
SCAN t-iBackbone=Faster R-CNN, biGRU, Params=13.68M2023.0813.25
SCAN i2tParms=60 M2023.1014.19
SCAN i-tBackbone=Faster R-CNN, biGRU, Params=13.68M2023.0814.23
CAMP-tripletBackbone=Faster R-CNN, biGRU, Params=27.03M2023.0814.39
CAMERAParms=64 M2023.1014.39
LW-MCR-bBackbone=SqueezeNet, -, Params=1.65M2023.0814.52
LW-MCR-dBackbone=SqueezeNet, -, Params=1.65M2023.0814.66
LW-MCR2023.1014.66
MTFNBackbone=Faster R-CNN, biGRU, Params=77.90M2023.0814.81
VSE++Parms=29 M2023.1014.89
Zero-shot CLIPBackbone=CLIP(ViT-B-32), Params=0.00M2023.0815.04
CAMPParms=63 M2023.1015.2
AMFMN-simBackbone=ResNet18, biGRU, Params=35.94M2023.0815.53
AMFMNParms=36 M2023.1015.53
LW-MCR-uBackbone=SqueezeNet, -, Params=1.65M2023.0815.59
SCAN t2iParms=60 M2023.1015.61
AMFMN-softBackbone=ResNet18, biGRU, Params=35.94M2023.0816.02
AMFMN-fusionBackbone=ResNet18, biGRU, Params=35.94M2023.0816.42
CoOpBackbone=CLIP(ViT-B-32), Params=0.10M2023.0817.29
CABIRBackbone=ResNet152, BERT+biGRU, Params=Not specified2023.0818.12
GaLR w/o MRBackbone=ResNet18, biGRU, Params=46.89M2023.0818.62
MCRNBackbone=ResNet18, biGRU, Params=52.35M2023.0818.95
GaLR with MRBackbone=ResNet18, biGRU, Params=46.89M2023.0818.96
GaLRParms=46 M2023.1018.96
VL-PromptBackbone=CLIP(ViT-B-32), Params=0.47M2023.0819.61
KCR2023.1019.89
HVSA2023.1020.16
DOVE-SParms=25 M2023.1020.4
SWANParms=40 M2023.1020.61
ConvpassBackbone=CLIP(ViT-B-32), Params=0.14M2023.0821.38
CLIP-AdapterBackbone=CLIP(ViT-B-32), Params=0.52M2023.0821.65
VPTBackbone=CLIP(ViT-B-32), Params=0.46M2023.0821.72
DOVEParms=38 M2023.1022.72
Linear probeBackbone=CLIP(ViT-B-32), Params=1.05M2023.0824.46
AdapterBackbone=CLIP(ViT-B-32), Params=0.17M2023.0824.84
Single LanguageBackbone=CLIP(ViT-B-32), Params=151M2023.0827.42
Cross-Modal AdapterBackbone=CLIP(ViT-B-32), Params=0.16M2023.0827.96
AdaptFormerBackbone=CLIP(ViT-B-32), Params=0.17M2023.0828.1
UniAdapterBackbone=CLIP(ViT-B-32), Params=0.55M2023.0828.84
Full fine-tuningBackbone=CLIP(ViT-B-32), Params=151M2023.0830.39
OursBackbone=CLIP(ViT-B-32), Params=0.16M2023.0831.12