List your company

Zero-shot Image-Text Retrieval on Flickr

99.5R@5 TROriginal CLIP
91.793.72595.7597.775Nov 19, 2024

Evaluation results

MethodLinks
Original CLIPBackbone=ViT-H/14, Biases=Gender2024.1199.594.1—
OursBackbone=ViT-H/14, Biases=Gender2024.1199.593.8—
Original CLIPBackbone=ViT-H/14, Biases=Age2024.1199.594.1—
OursBackbone=ViT-H/14, Biases=Age2024.1199.594—
Biased-promptsBackbone=ViT-H/14, Biases=Gender2024.1199.293.3—
CLIP-clipBackbone=ViT-H/14, Biases=Age2024.1199.293.8—
Biased-promptsBackbone=ViT-H/14, Biases=Age2024.1198.893—
CLIP-clipBackbone=ViT-H/14, Biases=Gender2024.1198.493—
OursBackbone=ViT-L/14, Biases=Age2024.1197.386.8—
Original CLIPBackbone=ViT-L/14, Biases=Gender2024.1197.287.2—
Original CLIPBackbone=ViT-L/14, Biases=Age2024.1197.287.2—
OursBackbone=ViT-L/14, Biases=Gender2024.119787—
CLIP-clipBackbone=ViT-L/14, Biases=Gender2024.1196.685.2—
Original CLIPBackbone=ViT-B/16, Biases=Gender2024.1196.485.5—
CLIP-clipBackbone=ViT-B/16, Biases=Gender2024.1196.483—
Original CLIPBackbone=ViT-B/16, Biases=Age2024.1196.485.5—
CLIP-clipBackbone=ViT-L/14, Biases=Age2024.1196.286.4—
CLIP-clipBackbone=ViT-B/16, Biases=Age2024.1196.184.5—
OursBackbone=ViT-B/16, Biases=Gender2024.1195.884.6—
OursBackbone=ViT-B/16, Biases=Age2024.1195.684.6—
Biased-promptsBackbone=ViT-L/14, Biases=Gender2024.1195.587.2—
Original CLIPBackbone=ViT-B/32, Biases=Gender2024.1194.783.5—
OursBackbone=ViT-B/32, Biases=Gender2024.1194.782.9—
Original CLIPBackbone=ViT-B/32, Biases=Age2024.1194.783.5—
Biased-promptsBackbone=ViT-L/14, Biases=Age2024.1194.586.6—
Biased-promptsBackbone=ViT-B/16, Biases=Gender2024.1194.386.1—
CLIP-clipBackbone=ViT-B/32, Biases=Age2024.1194.283.2—
Biased-promptsBackbone=ViT-B/16, Biases=Age2024.1194.185.2—
OursBackbone=ViT-B/32, Biases=Age2024.1194.182.5—
Biased-promptsBackbone=ViT-B/32, Biases=Gender2024.1193.682.4—
CLIP-clipBackbone=ViT-B/32, Biases=Gender2024.119381—
Biased-promptsBackbone=ViT-B/32, Biases=Age2024.119282.2—
Biased-promptsBackbone=ViT-B/162026.07——94.1
Biased-promptsBackbone=ViT-B/322026.07——91.9
Biased-promptsBackbone=ViT-B/162026.07——85.8
Biased-promptsBackbone=ViT-B/322026.07——83.34
CLIP-clipBackbone=ViT-B/162026.07——95.8
CLIP-clipBackbone=ViT-B/322026.07——93.6
CLIP-clipBackbone=ViT-B/162026.07——85.1
CLIP-clipBackbone=ViT-B/322026.07——81.74
Joint V-LBackbone=ViT-B/162026.07——96.5
Joint V-LBackbone=ViT-B/322026.07——94.6
Joint V-LBackbone=ViT-B/162026.07——83.8
Joint V-LBackbone=ViT-B/322026.07——82.4
Original CLIPBackbone=ViT-B/162026.07——96.4
Original CLIPBackbone=ViT-B/322026.07——94.7
Original CLIPBackbone=ViT-B/162026.07——85.5
Original CLIPBackbone=ViT-B/322026.07——83.5
RG-TTABackbone=ViT-B/162026.07——97.2
RG-TTABackbone=ViT-B/322026.07——97
RG-TTABackbone=ViT-B/162026.07——88.3
RG-TTABackbone=ViT-B/322026.07——86.5