List your company

Few-shot Image Classification on Average 11 datasets (test)

87.41Average Accuracy (Few-shot)CAPT
60.765267.682674.681.5174Sep 30, 2025Oct 28, 2025Nov 25, 2025Dec 23, 2025Jan 20, 2026Feb 17, 2026Mar 17, 2026

Evaluation results

MethodLinks
CAPTShot=16, Backbone=ViT-B/16 CLIP2026.0387.41—————
PromptKDShot=16, Backbone=ViT-B/16 CLIP2026.0386.96—————
2SFSShot=16, Backbone=ViT-B/16 CLIP2026.0385.5—————
CAPTShot=8, Backbone=ViT-B/16 CLIP2026.0381.91—————
SigLIP2Classifier=LDA, Embedding Projection=PCA<-, Backbone=ViT-B2026.0381—————
2SFSShot=8, Backbone=ViT-B/16 CLIP2026.0380.7—————
SigLIP2Classifier=LDA, Embedding Projection=Original, Backbone=ViT-B2026.0380.5—————
PromptKDShot=8, Backbone=ViT-B/16 CLIP2026.0379.56—————
SigLIPClassifier=LDA, Embedding Projection=PCA<-, Backbone=ViT-B2026.0379.4—————
SigLIP2Classifier=Prototype, Embedding Projection=PCA<-, Backbone=ViT-B2026.0379.4—————
CoOpShot=16, Backbone=ViT-B/16 CLIP2026.0379.01—————
SigLIPClassifier=LDA, Embedding Projection=Original, Backbone=ViT-B2026.0379—————
CAPTShot=4, Backbone=ViT-B/16 CLIP2026.0378.69—————
MaPLeShot=16, Backbone=ViT-B/16 CLIP2026.0378.55—————
2SFSShot=4, Backbone=ViT-B/16 CLIP2026.0378.5—————
SigLIPClassifier=Prototype, Embedding Projection=PCA<-, Backbone=ViT-B2026.0378.5—————
PromptKDShot=4, Backbone=ViT-B/16 CLIP2026.0378.46—————
SeMoBridge-TParam.=0.77 M, Avg. Time=27 s, Backbone=ViT-B/162025.0978.15—————
SeMoBridge-T w/o CSBParam.=0.26 M, Avg. Time=22 s, Backbone=ViT-B/162025.0978.14—————
PromptSRCParam.=0.05 M, Avg. Time=1 h 42 min, Backbone=ViT-B/162025.0977.9—————
APE-TParam.=0.51 M, Avg. Time=3 min 30 s, Backbone=ViT-B/162025.0977.18—————
LDCParam.=69 M, Avg. Time=2 min, Backbone=ViT-B/162025.0977.17—————
SigLIP2Classifier=Prototype, Embedding Projection=Original, Backbone=ViT-B2026.0377—————
CoOpShot=8, Backbone=ViT-B/16 CLIP2026.0376.45—————
SigLIPClassifier=Prototype, Embedding Projection=Original, Backbone=ViT-B2026.0376.3—————
Tip-Adapter-FParam.=16.3 M, Avg. Time=4 min, Backbone=ViT-B/162025.0975.9—————
CAPTShot=2, Backbone=ViT-B/16 CLIP2026.0375.83—————
DINOv2Classifier=LDA, Embedding Projection=Original, Backbone=ViT-B2026.0375.3—————
PromptKDShot=2, Backbone=ViT-B/16 CLIP2026.0375.19—————
MaPLeShot=8, Backbone=ViT-B/16 CLIP2026.0373.82—————
CoOpShot=4, Backbone=ViT-B/16 CLIP2026.0373.59—————
2SFSShot=2, Backbone=ViT-B/16 CLIP2026.0373.28—————
CAPTShot=1, Backbone=ViT-B/16 CLIP2026.0373.11—————
2SFSShot=1, Backbone=ViT-B/16 CLIP2026.0372.55—————
PromptKDShot=1, Backbone=ViT-B/16 CLIP2026.0372.47—————
DINOv2Classifier=Prototype, Embedding Projection=Original, Backbone=ViT-B2026.0371.8—————
CLIPClassifier=LDA, Embedding Projection=PCA<-, Backbone=ViT-B2026.0370.8—————
MaPLeShot=4, Backbone=ViT-B/16 CLIP2026.0370.66—————
CoOpShot=2, Backbone=ViT-B/16 CLIP2026.0370.13—————
CLIPClassifier=LDA, Embedding Projection=Original, Backbone=ViT-B2026.0369.8—————
CLIPClassifier=Prototype, Embedding Projection=PCA<-, Backbone=ViT-B2026.0369.7—————
CLIP-AdapterParam.=0.52 M, Avg. Time=32 min, Backbone=ViT-B/162025.0969.45—————
CoOpShot=1, Backbone=ViT-B/16 CLIP2026.0368.09—————
MaPLeShot=2, Backbone=ViT-B/16 CLIP2026.0365.28—————
CoOpParam.=0.01 M, Avg. Time=10 h 0 min, Backbone=ViT-B/162025.0963.9—————
CLIPClassifier=Prototype, Embedding Projection=Original, Backbone=ViT-B2026.0363.8—————
MaPLeShot=1, Backbone=ViT-B/16 CLIP2026.0361.79—————
CoCoOp2025.03—66.7967.6571.2172.9674.9
CoCoOp2025.05—66.7967.6571.2172.9674.9
CoOp2025.03—67.5670.6574.0276.9879.89
CoOp2025.05—67.5670.6574.0276.9879.89
Linear probe CLIP2025.03—45.8357.9868.0174.4778.79
Linear probe CLIP2025.05—45.8357.9868.0174.4778.79
MaPLe2025.03—69.2772.5875.3778.8981.79
MaPLe2025.05—69.2772.5875.3778.8981.79
MMA2025.03—69.2872.0876.3879.5782.76
MMA2025.05—69.2872.0876.3879.5782.76
MMRL2025.03—72.6775.979.281.4784.34
MMRL2025.05—72.6775.979.281.4784.34
MMRL++2025.05—72.6675.257981.3384.05
PromptSRC2025.03—72.3275.2978.3580.6982.87
PromptSRC2025.05—72.3275.2978.3580.6982.87