List your company
ResearchFormerly WizWand

Image Classification on Oxford-IIIT Pet (Top-1 Acc)

96.54Top-1 AccuracyDINOv3-B/16
46.193659.264372.33585.4057Jan 12, 2025Apr 6, 2025Jun 29, 2025Sep 21, 2025Dec 14, 2025Mar 8, 2026Jun 1, 2026
Updated 5mo ago

Evaluation results

MethodLinks
DINOv3-B/16Evaluation Protocol=Linear Probe2026.0596.54
DINOv2-reg-B/14Evaluation Protocol=Linear Probe2026.0595.97
VECA-B/16Evaluation Protocol=Linear Probe, Core tokens (C)=642026.0595.67
DINOv2-B/14Evaluation Protocol=Linear Probe2026.0595.61
VECA-B/16Evaluation Protocol=Linear Probe, Core tokens (C)=82026.0595.12
iBOTBackbone=ViT-L/16, Pre-training Epochs=250, Training Heuristics=w/ heuristics, Linear Probe Training Epochs=102026.0694
DINOBackbone=ViT-B/16, Pre-training Epochs=400, Training Heuristics=w/ heuristics, Linear Probe Training Epochs=102026.0693.6
iBOTBackbone=ViT-B/16, Pre-training Epochs=400, Training Heuristics=w/ heuristics, Linear Probe Training Epochs=102026.0693.6
DFNCLIP-B/16Evaluation Protocol=Linear Probe2026.0593.59
AM-RADIOv2.5-B/16Evaluation Protocol=Linear Probe2026.0593.54
SigLIP 2-B/16Evaluation Protocol=Linear Probe2026.0592.89
I-JEPABackbone=ViT-H/14, Pre-training Epochs=300, Training Heuristics=w/ heuristics, Linear Probe Training Epochs=102026.0692.8
CLIP-B/16Evaluation Protocol=Linear Probe2026.0592.72
OpenCLIP-B/16Evaluation Protocol=Linear Probe2026.0591.91
MAEBackbone=ViT-L/16, Pre-training Epochs=1600, Training Heuristics=w/o heuristics, Linear Probe Training Epochs=102026.0691.3
MoCoV3Backbone=ViT-B/16, Pre-training Epochs=300, Training Heuristics=w/ heuristics, Linear Probe Training Epochs=102026.0689.8
LeJEPA*Backbone=ViT-L/14, Pre-training Epochs=100, Training Heuristics=w/o heuristics, Linear Probe Training Epochs=1002026.0689.7
VISRegBackbone=ViT-L/14, Pre-training Epochs=400, Training Heuristics=w/o heuristics, Linear Probe Training Epochs=102026.0689.2
Grad-MimicNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0188.8
VISRegBackbone=ViT-L/14, Pre-training Epochs=100, Training Heuristics=w/o heuristics, Linear Probe Training Epochs=1002026.0688.7
Rho-LossNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0188.53
VISRegBackbone=ViT-B/16, Pre-training Epochs=400, Training Heuristics=w/o heuristics, Linear Probe Training Epochs=102026.0688.3
Grad-MimicNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0188.25
Rho-LossNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0187.79
SGDNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0187.33
Grad-MimicNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0187.14
Grad-MatchNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0186.86
Rho-LossNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0186.86
Grad-MatchNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0185.75
SGDNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0185.55
AGRANoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0185.25
SGDNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0183.51
Grad-MatchNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0183.18
data2vecBackbone=ViT-L/14, Pre-training Epochs=1600, Training Heuristics=w/ heuristics, Linear Probe Training Epochs=102026.0683
AGRANoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0182.53
AGRANoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0178.39
Grad-NormNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0169.47
Grad-NormNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0160.02
Grad-NormNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.0148.13