List your company
ResearchFormerly WizWand

Image Recognition on Describable Textures Dataset (DTD)

99.3AccuracyUNICOM
42.058456.919271.7886.6408Jan 16, 2024May 27, 2024Oct 6, 2024Feb 15, 2025Jun 27, 2025Nov 6, 2025Mar 18, 2026
Updated 7mo ago

Evaluation results

MethodLinks
UNICOMPre-training Data=LAION-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.0799.3
MLCDPre-training Data=LAION-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.0799.3
CLIPPre-training Data=WIT-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.0799.2
CLIP+Pre-training Data=WIT-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.0799.2
OpenCLIPPre-training Data=LAION-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.0798.8
AIMv2architecture=ViT-3B/14, Resolution=448px2024.1189
DINOv2Architecture=ViT-g/14, Pre-training Data=LVD, Resolution=518x518, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0186.3
AIM-7B†Architecture=ViT-7B/14, Pre-training Data=DFN-2B+, Feature Extraction Layer=20th, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0185.6
SARELearning Paradigm=Training-based2026.0383.1
AIM-7BArchitecture=ViT-7B/14, Pre-training Data=DFN-2B+, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0182.3
AIM-3BArchitecture=ViT-3B/14, Pre-training Data=DFN-2B+, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0181.9
AIM-1BArchitecture=ViT-1B/14, Pre-training Data=DFN-2B+, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0181.8
iBOTArchitecture=ViT-L/16, Pre-training Data=IN-21k, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0181.6
MAEArchitecture=ViT-2B/14, Pre-training Data=IG-3B, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0181.2
AIM-0.6BArchitecture=ViT-H/14, Pre-training Data=DFN-2B+, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0180.1
DINOArchitecture=ViT-B/8, Pre-training Data=IN-1k, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0178.4
MAEArchitecture=ViT-H/14, Pre-training Data=IN-1k, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0178.1
VT-FSLLearning Paradigm=Training-based2026.0376.31
UniFGVCLearning Paradigm=Training-free, Method Strategy=Reasoning-based2026.0373.9
Qwen2.5-VL-7BLearning Paradigm=Backbone2026.0368.83
BEiTArchitecture=ViT-L/14, Pre-training Data=IN-21k, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0164
FineDeficsLearning Paradigm=Training-based2026.0363.53
SCANLearning Paradigm=Training-free, Method Strategy=Retrieval-based2026.0362.65
AutoSEPLearning Paradigm=Training-free, Method Strategy=Reasoning-based2026.0361.47
ProtoMMLearning Paradigm=Training-free, Method Strategy=Retrieval-based2026.0356.38
AWTLearning Paradigm=Training-free, Method Strategy=Retrieval-based2026.0355.2
CascadeVLMLearning Paradigm=Training-free, Method Strategy=Reasoning-based2026.0353.24
SuS-X-LCLearning Paradigm=Training-free, Method Strategy=Retrieval-based2026.0352.34
E-FineRLearning Paradigm=Training-free, Method Strategy=Retrieval-based2026.0350.27
FineRLearning Paradigm=Training-free, Method Strategy=Retrieval-based2026.0349.76
RARLearning Paradigm=Training-free, Method Strategy=Retrieval-based2026.0349.57
CLIP-B/32Learning Paradigm=Backbone2026.0344.26