Our new X account is live! Follow @wizwand_team for updates

Text-to-Image Retrieval on Flickr30K-CN

84.4R@1

R2D2

Updated 3d ago

Evaluation Results

Method
R2D2 2022.11	84.4	96.7	98.4	-	-
CN-CLIP 2022.11	84.4	97.1	98.7	-	-
Arbitrary Ratio Feature Compression (ARFC) 2026.02	84.3	97.1	98.7	-	-
CN-CLIP 2022.11	83.8	96.9	98.6	-	-
Baseline 2026.02	83.8	96.9	98.6	-	-
Arbitrary Ratio Feature Compression (ARFC) 2026.02	83.4	96.9	98.5	-	-
AutoEncoder-VAE 2026.02	83.1	96.7	98.5	-	-
CN-CLIP 2022.11	82.7	96.7	98.6	-	-
Q-Former 2026.02	82.3	95.9	98.1	-	-
Arbitrary Ratio Feature Compression (ARFC) 2026.02	81.8	95.8	97.9	-	-
AutoEncoder-VAE 2026.02	81.7	95.7	98	-	-
M2-Encoder 2024.01	81.5	96.2	98.5	-	-
Q-Former 2026.02	80.3	95.4	97.9	-	-
AutoEncoder-VAE 2026.02	79.2	94.8	97.3	-	-
CN-CLIP 2022.11	79.1	94.8	97.4	-	-
GME 2026.02	79.1	-	-	-	-
M2-Encoder 2024.01	78.6	94.8	97.6	-	-
Qwen3-VL-Embedding 2026.02	78.6	-	-	-	-
R2D2 2022.11	78.3	94.6	97	-	-
Q-Former 2026.02	77.5	93.8	96.9	-	-
Wukong_ViT-L 2022.02	77.4	94.5	97	93.4	-
Wukong 2022.11	77.4	94.5	97	-	-
CLIP_ViT-L 2022.02	77.3	94.4	97.2	93.2	-
ObjEmbed 2026.02	77.3	-	-	-	-
FG-CLIP2 2026.02	77.2	-	-	-	-
FILIP_ViT-L 2022.02	76.9	94.9	97.4	93	-
ObjEmbed 2026.02	76.1	-	-	-	-
UME-R1 2026.02	75	-	-	-	-
Arbitrary Ratio Feature Compression (ARFC) 2026.02	73.4	92.1	96	-	-
PTQ-P4Q (8bit) 2026.02	73.1	91.6	95.6	-	-
PTQ-MinMax (8bit) 2026.02	72.8	91.5	95.5	-	-
M2-Encoder 2024.01	72.5	92.4	96.4	-	-
MetaCLIP2 2026.02	72.2	-	-	-	-
CN-CLIP 2022.11	71.2	91.4	95.5	-	-
CN-CLIP 2024.01	71.2	91.4	95.5	-	-
Baseline 2026.02	71.2	91.4	95.5	-	-
Arbitrary Ratio Feature Compression (ARFC) 2026.02	71.1	91.4	95.6	-	-
GME 2026.02	71.1	-	-	-	-
FILIP_Swin-L 2022.02	70.9	91.3	95.3	90	-
Arbitrary Ratio Feature Compression (ARFC) 2026.02	70.2	90.8	95.2	-	-
AltCLIP 2022.11	69.8	89.9	94.7	89.2	-
AltCLIP 2024.01	69.8	89.9	94.7	-	-
AutoEncoder-VAE 2026.02	69.8	90.6	95	-	-
CLIP_ViT-B 2022.02	69	90.3	95	89.7	-
CN-CLIP 2022.11	69	90.7	95.4	-	-
AutoEncoder-VAE 2026.02	68.3	89.5	94.7	-	-
Q-Former 2026.02	68.1	89.4	94.7	-	-
Arbitrary Ratio Feature Compression (ARFC) 2026.02	68.1	89.4	94.5	-	-
CN-CLIP 2022.11	68	89.7	94.4	87.9	-
CN-CLIP 2022.11	68	89.7	94.4	-	-
AutoEncoder-VAE 2026.02	67.8	89.4	93.7	-	-
Wukong_ViT-B 2022.02	67.6	89.6	94.2	88.7	-
Wukong 2022.11	67.6	89.6	94.2	-	-
CLIP_Swin-L 2022.02	67.4	90.3	94.9	89.1	-
Wukong_Swin-L 2022.02	67.4	89.9	94.5	89.3	-
VLM2Vec-V2 2026.02	67.1	-	-	-	-
CN-CLIP 2022.11	66.7	89.4	94.1	-	-
PTQ-P4Q (4bit) 2026.02	66.4	88.8	93.4	-	-
Q-Former 2026.02	66.4	88.6	93.5	-	-
PTQ-MinMax (4bit) 2026.02	65.8	88.4	93.2	-	-
Q-Former 2026.02	65.7	88.1	93.9	-	-
AutoEncoder-VAE 2026.02	63.8	87.2	93.1	-	-
AltCLIPT 2022.11	63.7	86.3	92.1	87.2	-
CN-CLIP 2022.11	62.7	86.9	92.8	-	-
CN-CLIP 2024.01	62.7	86.9	92.8	-	-
Q-Former 2026.02	61.9	86.5	92.3	-	-
R2D2 2022.11	60.9	86.8	92.7	85.6	-
R2D2 2022.11	60.9	86.8	92.7	-	-
R2D2 2022.05	60.9	86.8	92.7	-	85.6
R2D2 2024.01	60.9	86.8	92.7	-	-
Arbitrary Ratio Feature Compression (ARFC) 2026.02	60.5	85.2	91.4	-	-
FILIP_ViT-B 2022.02	57.5	84.3	90.6	81.9	-
VLM2Vec 2026.02	56.9	-	-	-	-
FILIP 2022.02	55.7	81.2	87.9	83	-
FILIP 2022.05	55.7	81.2	87.9	-	83
Taiyi 2022.11	53.7	79.8	86.6	78.4	-
Taiyi 2024.01	53.7	79.8	86.6	-	-
AutoEncoder-VAE 2026.02	52.5	79.1	86.9	-	-
CLIP 2022.02	51.8	78.6	85.9	80.6	-
CLIP 2022.05	51.8	78.6	85.9	-	80.6
Wukong 2022.02	51.7	78.9	86.3	80.9	-
Wukong 2022.11	51.7	78.9	86.3	80.9	-
Wukong 2022.11	51.7	78.9	86.3	-	-
Wukong 2022.05	51.7	78.9	86.3	-	80.9
Wukong 2024.01	51.7	78.9	86.3	-	-
SigLIP2 2026.02	51.7	-	-	-	-
Taisu 2024.01	49.9	78.9	87	-	-
Q-Former 2026.02	49.7	77.2	84.8	-	-
CN-CLIP 2022.11	48.8	76	84.6	-	-
CLIP 2022.02	47.2	74.1	82.9	77.5	-
Wukong 2022.02	45.7	73.8	82.2	75.1	-
Wukong 2022.11	45.7	73.8	82.2	-	-
FILIP 2022.02	44.6	72.2	81.2	74.7	-
CLIP 2022.02	41.2	69.7	80.2	73.2	-
Wukong 2022.02	40.9	68	78.4	70.9	-
FILIP 2022.02	28.7	55.9	67.1	58.8	-
BriVL 2022.02	10.3	27.5	37.9	31.7	-
BriVL 2024.01	10.3	27.5	37.9	-	-
CLIP 2022.11	0	2.4	4	5	-