List your company
ResearchFormerly WizWand

Image Classification on OxfordPets

95.9AccuracyPiSSA
90.866492.173293.4894.7868Feb 24, 2025May 10, 2025Jul 25, 2025Oct 9, 2025Dec 24, 2025Mar 10, 2026May 25, 2026
Updated 5mo ago

Evaluation results

MethodLinks
PiSSABackbone=ViT-Base, Rank=322026.0595.9
PiSSABackbone=ViT-Large, Memory=1229.9 MB2026.0595.7
LAGOBackbone=L/14, Zero-shot=true2026.0595.07
BiFTABackbone=L/14, Zero-shot=true2026.0594.96
CERSABackbone=ViT-Large, Memory=1232.3 MB2026.0594.9
FourierFTBackbone=ViT-Large, Method=FourierFT, # Params=480K2026.0594.84
SOT-GLPShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0394.8
LoRABackbone=ViT-Large, Memory=1229.9 MB2026.0594.8
MMRLmode=Target Evaluation2025.0594.67
WCABackbone=L/14, Zero-shot=true2026.0594.66
Uni-LoRABackbone=ViT-Large, Method=Uni-LoRA, # Params=144K2026.0594.65
MMRL++mode=Target Evaluation2025.0594.63
FourierFTBackbone=ViT-Large, Method=FourierFT, # Params=144K2026.0594.46
CoOpOpmode=Target Evaluation2025.0594.43
FFBackbone=ViT-Large, Method=FF, # Params=303.3M2026.0594.43
FTBackbone=ViT-Large, Memory=4629.8 MB2026.0594.4
EBMmode=Fine-tuning2025.1094.4
CuPLBackbone=L/14, Zero-shot=true2026.0594.33
GalLoPShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0394.1
Uni-LoRABackbone=ViT-Base, Method=Uni-LoRA, # Params=72K2026.0594
TCPmode=Target Evaluation2025.0593.97
GPartBackbone=ViT-Large, Method=GPart (Ours), # Params=144K2026.0593.86
GPartBackbone=ViT-Base, Method=GPart (Ours), # Params=72K2026.0593.85
MMAmode=Target Evaluation2025.0593.8
SCANShot=162025.0593.78
CoOpmode=Target Evaluation2025.0593.7
PromptSRCShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0393.7
PromptSRCmode=Fine-tuning2025.1093.7
CLIP-EBackbone=L/14, Zero-shot=true2026.0593.62
PromptSRCmode=Target Evaluation2025.0593.6
PLOTShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0393.6
PLOTmode=Fine-tuning2025.1093.6
MaPLemode=Target Evaluation2025.0593.53
ProDAShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0393.5
TOGAShots=8, Venue=-2026.0393.4
TOGAShots=16, Venue=-2026.0393.4
SVFitBackbone=ViT-Large, Memory=1351.5 MB2026.0593.4
CoCoOpShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0393.3
CLIP-DBackbone=L/14, Zero-shot=true2026.0593.3
SVFTBackbone=ViT-Large, Memory=1355.8 MB2026.0593.3
CoCoOpmode=Fine-tuning2025.1093.3
CLIPBackbone=L/14, Zero-shot=true2026.0593.24
FourierFTBackbone=ViT-Base, Method=FourierFT, # Params=72K2026.0593.21
CERSABackbone=ViT-Base, α=0.95, β=0.952026.0593.2
CoFT+mode=unsupervised fine-tuning2026.0293.16
FFBackbone=ViT-Base, Method=FF, # Params=85.8M2026.0593.14
FTBackbone=ViT-Base2026.0593.1
LoRABackbone=ViT-Base, Rank=322026.0593.1
FourierFTBackbone=ViT-Base, Method=FourierFT, # Params=239K2026.0593.05
CS-AlignerBackbone=ViT-B/16, Number of Shots=16, Evaluation Protocol=fine-tuned2025.0293
MaPLeShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0392.8
MaPLemode=Fine-tuning2025.1092.8
MMRL + MetaTPTadaptation=MetaTPT2025.1292.79
LAGOBackbone=B/16, Zero-shot=true2026.0592.78
CLIP-Adapter (best α)Backbone=ViT-B/16, Shots=16, Blending ratio (alpha) selection strategy=Best residual ratio per dataset (oracle)2026.0392.7
CLIP-AdapterBackbone=ViT-B/16, Shots=16, Blending ratio (alpha)=best2026.0392.7
TOGAShots=4, Venue=-2026.0392.7
CLIP-Adapter (α = 0.2)Backbone=ViT-B/16, Shots=16, Blending ratio (alpha) selection strategy=Fixed residual ratio (α = 0.2), selected on ImageNet2026.0392.6
CLIP-AdapterBackbone=ViT-B/16, Shots=16, Blending ratio (alpha)=0.22026.0392.6
CAPTrole=Target2026.0392.53
LwEIBrole=Target2026.0392.5
SVFTBackbone=ViT-Base2026.0592.5
CoFTmode=unsupervised fine-tuning2026.0292.4
LoCoOpShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0392.4
CLIP-MoETraining shots=16-shot, Source dataset=ImageNet, Training epochs=32026.0392.3
SVFitBackbone=ViT-Base, Rank=7682026.0592.3
SCANShot=82025.0592.29
HOSO-AdapterBackbone=ViT-B/16, Shots=16, Blending ratio (alpha) selection strategy=Optimised on hold-one-shot-out cache2026.0392.27
HOSO-AdapterBackbone=ViT-B/16, Shots=16, Number of runs=32026.0392.27
WCABackbone=B/16, Zero-shot=true2026.0592.23
TOGAShots=2, Venue=-2026.0392.2
CLIP-AdapterBackbone=ViT-B/16, Number of Shots=16, Evaluation Protocol=fine-tuned2025.0292.1
CoOpShots=16, Backbone=ViT-B/16, Pre-training=CLIP2026.0391.9
CoOpmode=Fine-tuning2025.1091.9
VaMPCross-dataset evaluation protocol=true, Zero-shot transfer=true2025.1191.79
GRIPmode=unsupervised fine-tuning2026.0291.69
BiFTABackbone=B/16, Zero-shot=true2026.0591.67
CLIP-MoE + MoE-GRPOTraining shots=16-shot, Source dataset=ImageNet, Training epochs=32026.0391.6
PromptKDrole=Target2026.0391.59
WaffleBackbone=L/14, Zero-shot=true2026.0591.55
MMRLCross-dataset evaluation protocol=true, Zero-shot transfer=true2025.1191.43
MMRLvariant=standard2025.1291.43
MMRLadaptation=none2025.1291.43
MMRL++Backbone=ViT-B/16, Training Shots=16-shot2026.0591.43
MMRL2026.0591.43
MMRL + NeRP2026.0591.43
MMRLBackbone=ViT-B/16, Training Shots=16-shot, Training Source=ImageNet2026.0591.43
MAILBackbone=ViT-B/16, Training Shots=16-shot, Training Source=ImageNet2026.0591.37
A3B2Backbone=ViT-B/16, Training Shots=16-shot2026.0591.36
SCANShot=42025.0591.33
MMRL + TPTadaptation=TPT2025.1291.31
MMRLBackbone=ViT-B/16, Training Shots=16-shot2026.0591.31
TCPCross-dataset evaluation protocol=true, Zero-shot transfer=true2025.1191.25
TCPBackbone=ViT-B/16, Training Shots=16-shot, Training Source=ImageNet2026.0591.25
MMRLvariant=†2025.1291.23
TOGAShots=1, Venue=-2026.0391.2
MAIL++Backbone=ViT-B/16, Training Shots=16-shot, Training Source=ImageNet2026.0591.2
CuPLBackbone=B/16, Zero-shot=true2026.0591.14
LPBackbone=ViT-Large, Method=LP, # Params=02026.0591.11
CLIP-SVD2025.0991.06