List your company

Image Retrieval on Flickr30K 1K (test)

91.1R@1X-FMbase
37.33251.29165.2579.209Sep 15, 2022Apr 29, 2023Dec 11, 2023Jul 24, 2024Mar 7, 2025Oct 19, 2025Jun 2, 2026

Evaluation results

MethodLinks
X-FMbaseParameters=327M, Evaluation Protocol=Fine-Tuned, Training Data=More Data2023.0191.198.599.4—
X2-VLMbaseParameters=255M, Evaluation Protocol=Fine-Tuned, Training Data=More Data2023.0190.498.299.3—
CoCaParameters=2.1B, Evaluation Protocol=Fine-Tuned, Training Data=Super-Large2023.0190.398.799.5—
X-FMbaseParameters=327M, Evaluation Protocol=Fine-Tuned, Training Data=Standard2023.019098.699.3—
X2-VLMbaseParameters=255M, Evaluation Protocol=Fine-Tuned, Training Data=Standard2023.0188.697.998.9—
mPLUG-2Base#PT Data=17M2023.0288.297.899—
mPLUG-2#PT Data=17M2023.0288.197.699.1—
Florence#PT Data=0.9B2023.0287.998.1——
Florence# Img-Text Pairs=900M, Fine-tuned=true2022.0987.998.1——
OmniVL# Img-Text Pairs=14M*, Fine-tuned=true2022.0987.997.899.1—
BLIP#PT Data=129M2023.0287.697.799—
BLIP2023.0587.697.799—
BLIP# Img-Text Pairs=14M, Fine-tuned=true2022.0987.297.598.8—
X-VLMParameters=216M, Evaluation Protocol=Fine-Tuned, Training Data=Standard2023.0186.197.498.7—
RaSa2023.0585.997.5498.72—
ALBEF#PT Data=14M2023.0285.697.598.9—
ALBEF# Img-Text Pairs=14M, Fine-tuned=true2022.0985.697.598.9—
ALBEFconfiguration=backbone2023.0585.4497.3498.7—
METER + EPICData=4M, EPIC=true, Protocol=Fine-tuned2022.1185.197.498.7—
ALIGN#PT Data=1.8B2023.0284.997.498.6—
ALIGN2023.0584.997.498.6—
ALIGN# Img-Text Pairs=1.8B, Fine-tuned=true2022.0984.997.498.6—
VLMo#PT Data=4M2023.0284.597.398.6—
X-FMbaseParameters=327M, Evaluation Protocol=Zero-Shot, Training Data=More Data2023.0184.196.598.1—
VL-BEITParameters=175M, Evaluation Protocol=Fine-Tuned, Training Data=Standard2023.0183.9———
METERData=4M, EPIC=false, Protocol=Fine-tuned2022.1183.897.398.6—
OmniVLParameters=288M, Evaluation Protocol=Fine-Tuned, Training Data=Standard2023.0183.49798.6—
OmniVL# Img-Text Pairs=4M*, Fine-tuned=true2022.0983.49798.6—
ALBEFParameters=210M, Evaluation Protocol=Fine-Tuned, Training Data=Standard2023.0182.896.798.4—
METER# Img-Text Pairs=404M, Fine-tuned=true2022.0982.296.398.4—
CoCaParameters=2.1B, Evaluation Protocol=Zero-Shot, Training Data=Super-Large2023.0180.495.797.7—
VLMbaseParameters=175M, Evaluation Protocol=Fine-Tuned, Training Data=Standard2023.0179.395.797.8—
VLMO# Img-Text Pairs=4M, Fine-tuned=true2022.0979.395.797.8—
X2-VLMbaseParameters=255M, Evaluation Protocol=Zero-Shot, Training Data=More Data2023.0179.296.498—
X2-VLMbaseParameters=255M, Evaluation Protocol=Zero-Shot, Training Data=Standard2023.0179.195.297.3—
METER + EPICData=4M, EPIC=true, Protocol=Zero-shot2022.117994.597.1—
METERData=4M, EPIC=false, Protocol=Zero-shot2022.1178.894.596.9—
UNIMO2023.0578.0494.2497.12—
UNIMO#PT Data=4M2023.027894.297.1—
UNIMO# Img-Text Pairs=4M, Fine-tuned=true2022.097894.297.1—
X-FMbaseParameters=327M, Evaluation Protocol=Zero-Shot, Training Data=Standard2023.0177.395.397.6—
FlorenceParameters=893M, Evaluation Protocol=Zero-Shot, Training Data=More Data2023.0176.793.6——
ALIGNParameters=490M, Evaluation Protocol=Zero-Shot, Training Data=More Data2023.0175.793.896.8—
UNITER#PT Data=4M2023.0275.694.196.8—
COOKIE2023.0575.694.697.2—
UNITER# Img-Text Pairs=4M, Fine-tuned=true2022.0975.694.196.8—
UNITER2023.0575.5694.0896.76—
E2E-VLP#PT Data=4M2023.0273.692.496—
FLAVA# Img-Text Pairs=70M, Fine-tuned=true2022.0973.292.795.5—
X-VLMParameters=216M, Evaluation Protocol=Zero-Shot, Training Data=Standard2023.0171.993.396.4—
CLIPParameters=490M, Evaluation Protocol=Zero-Shot, Training Data=More Data2023.0168.790.695.2—
RCARWarm-up=true, Model Variant=All2023.0362.685.891.1—
RCARWarm-up=true, Model Variant=T2I2023.0360.984.490.1—
PCSR (AAAI'24)Noise=0.22026.0660.983.789.4505.7
GPOWarm-up=true, Ensemble=true2023.0360.886.392.3—
SPS (IJCAI'24)Noise=0.22026.0660.584.389.8507.1
IN2RNoise=0.22026.0660.586.291.7511.6
BiCro (CVPR'23)Noise=0.22026.0660.484.489.9504.7
GSC (CVPR'24)Noise=0.22026.0660.184.590.5505.8
L2RM (CVPR'24)Noise=0.22026.0659.883.689.5503.8
RCARModel Variant=All2023.0359.58489.5—
ESC (CVPR'24)Noise=0.22026.0659.183.889.1503.3
RCARWarm-up=true, Model Variant=I2T2023.0358.883.989.3—
CREAM (TIP'24)Noise=0.22026.0658.784.189.8502.3
IN2RNoise=0.42026.0658.784.790.7504.1
SGRAFBackbone=ResNet-101 BUTD [5]2023.0358.58388.8—
GPOWarm-up=true2023.0358.384.690.8—
GSC (CVPR'24)Noise=0.42026.0657.582.788.9497.3
GSMNBackbone=ResNet-101 BUTD [5]2023.0357.482.389—
PCSR (AAAI'24)Noise=0.42026.0657.482.488.9497.1
SPS (IJCAI'24)Noise=0.42026.0657.383.589.6498.9
RCARModel Variant=T2I2023.0357.282.888.5—
CREAM (TIP'24)Noise=0.42026.065782.688.7495
NCR (NeurIPS'21)Noise=0.22026.0656.982.488.5491.1
IN2RNoise=0.62026.0656.582.989.5495.2
L2RM (CVPR'24)Noise=0.42026.0656.38187.3490.5
NCR (NeurIPS'21)Noise=0.42026.0656.280.687.4486.8
ESC (CVPR'24)Noise=0.42026.065680.887.2489.6
BiCro (CVPR'23)Noise=0.42026.0655.58187.4487.5
SHANBackbone=ResNet-101 BUTD [5]2023.0355.381.388.4—
MMCABackbone=ResNet-101 BUTD [5]2023.0354.881.487.8—
WCGLBackbone=ResNet-101 BUTD [5]2023.0354.880.687.5—
PCSR (AAAI'24)Noise=0.62026.0654.879.786.5480.5
VSRNBackbone=ResNet-101 BUTD [5]2023.0354.781.888.2—
RCARModel Variant=I2T2023.0354.680.587—
IMRAMBackbone=ResNet-101 BUTD [5]2023.0353.979.487.2—
SPS (IJCAI'24)Noise=0.62026.0653.780.287.7484.1
SCANWarm-up=true2023.0353.681.288.6—
GSC (CVPR'24)Noise=0.62026.0653.679.886.8478
CREAM (TIP'24)Noise=0.62026.0653.379.287477.4
ESC (CVPR'24)Noise=0.62026.065378.685.3475
CAANBackbone=ResNet-101 BUTD [5]2023.0352.87987.9—
NCR (NeurIPS'21)Noise=0.62026.065277.684.9468.6
L2RM (CVPR'24)Noise=0.62026.0651.376.483.7467.6
BiCro (CVPR'23)Noise=0.62026.0651.277.684.7466.3
SCANBackbone=ResNet-101 BUTD [5]2023.0348.677.785.2—
IN2RNoise=0.82026.0648.276.484.7458.8
PCSR (AAAI'24)Noise=0.82026.0644.670.978.6437.5
CREAM (TIP'24)Noise=0.82026.0640.867.176.3416.3
L2RM (CVPR'24)Noise=0.82026.0639.465.474.9404