List your company
ResearchFormerly WizWand

Image Classification on Aircraft

94.8AccuracyKNN
46.408858.971971.53584.0981May 13, 2019Jun 24, 2020Aug 7, 2021Sep 20, 2022Nov 2, 2023Dec 15, 2024Jan 28, 2026
Updated 6mo ago

Evaluation results

MethodLinks
KNNSelection Method=KNN, Adaptation Strategy=Full, Training Epochs=4e, Backbone Architecture=Resnet-50-v22020.0994.8
KLSelection Method=KL, Adaptation Strategy=Full, Training Epochs=2e, Backbone Architecture=Resnet-50-v22020.0994.6
KNNSelection Method=KNN, Adaptation Strategy=Full, Training Epochs=2e, Backbone Architecture=Resnet-50-v22020.0994.5
KLSelection Method=KL, Adaptation Strategy=Full, Training Epochs=4e, Backbone Architecture=Resnet-50-v22020.0994.4
MetaFormerBackbone=MetaFormer-1, Pretrain=iNat212022.0394.3
EPNSelection Method=EPN, Adaptation Strategy=Full, Training Epochs=4e, Backbone Architecture=Resnet-50-v22020.0994.2
MetaFormerBackbone=MetaFormer-1, Pretrain=ImageNet-21k2022.0394.2
Dom-Ad (In-v3)Backbone Architecture=Inception-v32020.0994.1
CAPBackbone=Xception, Pretrain=ImageNet-1k2022.0394.1
EPNSelection Method=EPN, Adaptation Strategy=Full, Training Epochs=2e, Backbone Architecture=Resnet-50-v22020.0994
API-NetBackbone=DenseNet-161, Pretrain=ImageNet-1k2022.0393.9
PMGBackbone=ResNet-50, Pretrain=ImageNet-1k2022.0393.4
DCLBackbone=ResNet-50, Pretrain=ImageNet-1k2022.0393
Dom-Ad (Am-B)Backbone Architecture=AmoebaNet-B2020.0992.8
S3NBackbone=ResNet-50, Pretrain=ImageNet-1k2022.0392.8
MetaFormerBackbone=MetaFormer-1, Pretrain=ImageNet-1k2022.0392.8
GPipeBackbone=AmoebaNet-B, Pretrain=ImageNet-1k2022.0392.7
KNNSelection Method=KNN, Adaptation Strategy=Adapters, Training Epochs=4e, Backbone Architecture=Resnet-50-v22020.0992.5
KLSelection Method=KL, Adaptation Strategy=Adapters, Training Epochs=4e, Backbone Architecture=Resnet-50-v22020.0992.1
EPNSelection Method=EPN, Adaptation Strategy=Adapters, Training Epochs=4e, Backbone Architecture=Resnet-50-v22020.0992.1
BaselineBackbone Architecture=Resnet-50-v22020.0991.4
Core-tuningBackbone=ResNet-50, Pre-training=MoCo-v22021.0289.48
FNCEvaluation Protocol=Fine-tuned, Backbone=ResNet, Pre-training Dataset=ImageNet2020.1188.5
BYOLArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.0688.1
SimCLRArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.0688.1
SimCLR v1Evaluation Protocol=Fine-tuned, Backbone=ResNet, Pre-training Dataset=ImageNet2020.1188.1
BYOLEvaluation Protocol=Fine-tuned, Backbone=ResNet, Pre-training Dataset=ImageNet2020.1188.1
SimCLR (repro)Architecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.0687.6
RIFLEBackbone=ResNet-50, Pre-training=MoCo-v22021.0287.6
SimCLR v2Evaluation Protocol=Fine-tuned, Backbone=ResNet, Pre-training Dataset=ImageNet2020.1187.6
M&MBackbone=ResNet-50, Pre-training=MoCo-v22021.0287.45
SCLBackbone=ResNet-50, Pre-training=MoCo-v22021.0287.44
Bi-tuningBackbone=ResNet-50, Pre-training=MoCo-v22021.0287.39
BSSBackbone=ResNet-50, Pre-training=MoCo-v22021.0287.18
DELTABackbone=ResNet-50, Pre-training=MoCo-v22021.0287.05
SL-CE-tuningBackbone=ResNet-50, Pre-training=Supervised ImageNet2021.0287.03
CE-tuningBackbone=ResNet-50, Pre-training=MoCo-v22021.0286.87
L2SPBackbone=ResNet-50, Pre-training=MoCo-v22021.0286.55
Supervised-INArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.0686
Random initArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.0685.9
LRWOpt2024.0381.78
LRW-Hard2024.0381.28
LRW-Easy2024.0380.87
LRW-Random2024.0380.69
MAPLE2024.0380.58
FSR2024.0380.55
BILAW2024.0380.37
RHO-LOSS2024.0380.34
ERM2024.0380.22
LOUPEevaluation=linear probing2022.0880.2
MBW2024.0380.12
MWN2024.0380.11
ZLaPBatch Size=1000, Backbone=ViT-B/16, Keff=Medium (5-25), Protocol=Batch test-time adaptation2025.0175.4
HSMLWay=5, Shot=52019.0573.49
CLIPevaluation=linear probing2022.0869.4
MUMOMAMLWay=5, Shot=52019.0567.31
CoCoOpBackbone=ViT-B/16, Evaluation Protocol=16-shot ImageNet tuned2022.0966.89
Meta-SGDWay=5, Shot=52019.0566.84
MAMLWay=5, Shot=52019.0566.18
BMAMLWay=5, Shot=52019.0565.74
Prompt EnsembleBackbone=ViT-B/16, Evaluation Protocol=Zero-shot2022.0965.63
TPTBackbone=ViT-B/16, Evaluation Protocol=Zero-shot2022.0965.5
CoOpBackbone=ViT-B/16, Evaluation Protocol=16-shot ImageNet tuned2022.0964.15
MT-NetWay=5, Shot=52019.0563.03
StableRepPre-training Data Source=Synthetic, Evaluation Protocol=5-way, 5-shot2023.0662.6
StableRepPre-training dataset=CC12M, Pre-training data source=Syn, Evaluation protocol=Few-shot2023.0662.6
CLIPBackbone=ViT-B/16, Evaluation Protocol=Zero-shot2022.0962.59
CLIPPre-training Data Source=Real, Evaluation Protocol=5-way, 5-shot2023.0662
CLIPPre-training dataset=CC12M, Pre-training data source=Real, Evaluation protocol=Few-shot2023.0662
TPTBackbone=ResNet-50, Evaluation Protocol=Zero-shot2022.0961.46
FNCEvaluation Protocol=Linear eval, Backbone=ResNet, Pre-training Dataset=ImageNet2020.1161.3
CLIPPre-training Data Source=Synthetic, Evaluation Protocol=5-way, 5-shot2023.0661.3
CLIPPre-training dataset=CC12M, Pre-training data source=Syn, Evaluation protocol=Few-shot2023.0661.3
Supervised-INArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Linear evaluation2020.0661
Prompt EnsembleBackbone=ResNet-50, Evaluation Protocol=Zero-shot2022.0960.85
BYOLArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Linear evaluation2020.0660.6
BYOLEvaluation Protocol=Linear eval, Backbone=ResNet, Pre-training Dataset=ImageNet2020.1160.6
CoCoOpBackbone=ResNet-50, Evaluation Protocol=16-shot ImageNet tuned2022.0959.61
CLIPLinear evaluation=true, Model size=Base, Patch size=16*16, Resolution=224*2242023.0159.5
CLIPBackbone=ResNet-50, Evaluation Protocol=Zero-shot2022.0958.8
CoOpBackbone=ResNet-50, Evaluation Protocol=16-shot ImageNet tuned2022.0958.15
HSMLWay=5, Shot=12019.0557.38
StableRepPre-training dataset=RedCaps, Pre-training data source=Syn, Evaluation protocol=Few-shot2023.0657.3
CLIPPre-training dataset=RedCaps, Pre-training data source=Syn, Evaluation protocol=Few-shot2023.0655.2
CLIPPre-training dataset=RedCaps, Pre-training data source=Real, Evaluation protocol=Few-shot2023.0654.5
BMAMLWay=5, Shot=12019.0553.63
MUMOMAMLWay=5, Shot=12019.0553.14
PyramidCLIPTask=Linear Probe, Pretrain Dataset=143M, Image Encoder=ResNet502022.0453.1
Meta-SGDWay=5, Shot=12019.0552.99
IOTAShot=16-shot, Backbone=ViT-B/162026.0152.84
MAMLWay=5, Shot=12019.0551.37
SimCLR v2Evaluation Protocol=Linear eval, Backbone=ResNet, Pre-training Dataset=ImageNet2020.1151.1
SimCLRArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Linear evaluation2020.0650.3
SimCLR v1Evaluation Protocol=Linear eval, Backbone=ResNet, Pre-training Dataset=ImageNet2020.1150.3
SimCLR (repro)Architecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Linear evaluation2020.0649.8
DaVinciLinear evaluation=true, Model size=Base, Patch size=16*16, Resolution=224*2242023.0149.6
CLIPTask=Linear Probe, Pretrain Dataset=400M, Image Encoder=ResNet502022.0449.1
X+OS_SimCorepretrain=Target + SimCore, p=1%2023.0348.45
DeCLIPTask=Linear Probe, Pretrain Dataset=88M, Image Encoder=ResNet502022.0448.4
X+OS_SimCorepretrain=Target + SimCore, p=Adaptive, Criterion=Stopping Criterion2023.0348.27