List your company
ResearchFormerly WizWand

Few-Shot Classification on mini-ImageNet (test)

92.18AccuracyUnits-NTS
37.68451.83265.9880.128Mar 23, 2022Jul 3, 2022Oct 14, 2022Jan 25, 2023May 8, 2023Aug 19, 2023Nov 30, 2023
Updated 8mo ago

Evaluation results

MethodLinks
Units-NTSMeta-Training Dataset=mini-ImageNet, Uncertainty Threshold=0.12022.0392.18——
SemFew-TransBackbone=Swin-T, Way=5-way, Shot=5-shot, Method Category=Semantic-Based2023.1186.49——
FewTUREBackbone=Swin-T, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1186.38——
FGFLBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1186.01——
SP-CLIPBackbone=Visformer-T, Way=5-way, Shot=5-shot, Method Category=Semantic-Based2023.1183.42——
SVAE-ProtoBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Semantic-Based2023.1183.28——
Units-NTSMeta-Training Dataset=mini-ImageNet, Uncertainty Threshold=0.22022.0383.27——
SUNBackbone=ViT-S, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1183.25——
SemFewBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Semantic-Based2023.1183.04——
FEATBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1182.05——
AM3-BERTBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Semantic-Based2023.1181.29——
ProtoNetBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1180.53——
CTMBackbone=ResNet-18, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1180.51——
RFSBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1179.64——
TRAMLBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Semantic-Based2023.1179.54——
CANBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1179.44——
Meta-BaselineBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1179.26——
SemFew-TransBackbone=Swin-T, Way=5-way, Shot=1-shot, Method Category=Semantic-Based2023.1178.94——
MatchNetBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1178.72——
AM3Backbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Semantic-Based2023.1178.1——
Meta-AdaMBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1177.92——
SemFewBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Semantic-Based2023.1177.63——
TADAMBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1176.7——
SVAE-ProtoBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Semantic-Based2023.1174.84——
KTNBackbone=Conv-128, Way=5-way, Shot=5-shot, Method Category=Semantic-Based2023.1174.16——
FewTUREBackbone=Swin-T, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1172.4——
SP-CLIPBackbone=Visformer-T, Way=5-way, Shot=1-shot, Method Category=Semantic-Based2023.1172.31——
Units-NTSMeta-Training Dataset=mini-ImageNet2022.0371.7——
Bayesian TAMLMeta-Training Dataset=mini-ImageNet2022.0371.46——
Meta-SGDMeta-Training Dataset=mini-ImageNet2022.0369.95——
FGFLBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1169.14——
fo-Proto-MAMLMeta-Training Dataset=mini-ImageNet2022.0368.96——
TraNFS-3noise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.53——
Mediannoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.45——
AM3-BERTBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Semantic-Based2023.1168.42——
RNNPnoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.38——
Euclideannoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.32——
TraNFS-2noise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.29——
Vanilla ProtoNetnoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.27——
Absolutenoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.24——
Cosinenoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.2——
Oraclenoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0468.18——
Baseline++noise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0467.91——
SUNBackbone=ViT-S, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1167.8——
TRAMLBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Semantic-Based2023.1167.1——
FEATBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1166.78——
Linear Classifiernoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0466.65——
MAMLMeta-Training Dataset=mini-ImageNet2022.0366.61——
Oraclenoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0466.08——
MatchNetBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1165.64——
AM3Backbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Semantic-Based2023.1165.3——
TraNFS-3noise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0465.08——
TraNFS-2noise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0464.74——
KTNBackbone=Conv-128, Way=5-way, Shot=1-shot, Method Category=Semantic-Based2023.1164.42——
CTMBackbone=ResNet-18, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1164.12——
CANBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1163.85——
Absolutenoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0463.46——
Cosinenoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0463.46——
MAMLnoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0463.25——
Mediannoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0463.19——
Meta-BaselineBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1163.17——
Euclideannoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0463.02——
Oraclenoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0462.6——
Vanilla ProtoNetnoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0462.43——
RNNPnoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0462.43——
ProtoNetBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1162.39——
Matching Networksnoise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0462.16——
RFSBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1162.02——
Baseline++noise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0461.87——
Meta-AdaMBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1159.89——
TADAMBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1158.5——
Linear Classifiernoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0458.41——
MAMLBackbone=ResNet-12, Way=5-way, Shot=5-shot, Method Category=Visual-Based2023.1158.05——
Oraclenoise_proportion=60%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0456.89——
TraNFS-3noise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0456.65——
Matching Networksnoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0456.21——
Nearest k=5noise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0456.15——
TraNFS-2noise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0456.14——
Nearest k=1noise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0455.91——
Nearest k=3noise_proportion=0%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0455.29——
MAMLnoise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0453.28——
Cosinenoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0452.42——
Euclideannoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0452.09——
Absolutenoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0452.06——
Baseline++noise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0451.87——
Mediannoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0451.86——
RNNPnoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0451.62——
Vanilla ProtoNetnoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0451.41——
Nearest k=5noise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0450.92——
MAMLBackbone=ResNet-12, Way=5-way, Shot=1-shot, Method Category=Visual-Based2023.1149.24——
Nearest k=3noise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0448.43——
Nearest k=1noise_proportion=20%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0447.27——
Linear Classifiernoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0447.23——
Matching Networksnoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0446.18——
TraNFS-3noise_proportion=60%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0442.6——
MAMLnoise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0442.58——
TraNFS-2noise_proportion=60%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0442.24——
Nearest k=5noise_proportion=40%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0442.12——
Cosinenoise_proportion=60%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0439.9——
Absolutenoise_proportion=60%, shots=5-shot, ways=5-way, noise_type=symmetric label swap2022.0439.78——