Few-Shot Image Classification on CIFAR-FS 5-way (5-shot)

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	CAML [Laion-2b]	93.5	Yes	Context-Aware Meta-Learning	2023-10-17	Code
2	PT+MAP+SF+SOT (transductive)	92.83	No	The Self-Optimal-Transport Feature Transform	2022-04-06	Code
3	PT+MAP+SF+BPA (transductive)	92.83	No	The Balanced-Pairwise-Affinities Feature Transform	2024-06-25	Code
4	P>M>F (P=DINO-ViT-base, M=ProtoNet)	92.2	Yes	Pushing the Limits of Simple Pipelines for Few-S...	2022-04-15	Code
5	PEMnE-BMS*	91.86	No	Squeezing Backbone Feature Distributions to the ...	2021-10-18	Code
6	Illumination Augmentation	91.09	No	Sill-Net: Feature Augmentation with Separated Il...	2021-02-06	Code
7	LST+MAP	90.73	No	Transfer learning based few-shot classification ...	2021-02-09	Code
8	PT+MAP	90.68	No	Leveraging the Feature Distribution in Transfer-...	2020-06-06	Code
9	BAVARDAGE	90.63	No	Adaptive Dimension Reduction and Variational Inf...	2022-09-18	-
10	HCTransformers	90.5	No	Attribute Surrogates Learning and Spectral Token...	2022-03-17	Code
11	EASY 3xResNet12 (transductive)	90.47	No	EASY: Ensemble Augmented-Shot Y-shaped Learning:...	2022-01-24	Code
12	EASY 2xResNet12 1/√2 (transductive)	90.2	No	EASY: Ensemble Augmented-Shot Y-shaped Learning:...	2022-01-24	Code
13	Invariance-Equivariance	89.74	No	Exploring Complementary Strengths of Invariant a...	2021-03-01	Code
14	ACC + Amphibian	89.3	No	Generalized Adaptation for Few-Shot Learning	2019-11-25	-
15	pseudo-shots	89.12	No	Extended Few-Shot Learning: Exploiting Existing ...	2020-12-13	Code
16	EASY 3xResNet12 (inductive)	89	No	EASY: Ensemble Augmented-Shot Y-shaped Learning:...	2022-01-24	Code
17	SKD	88.9	No	Self-supervised Knowledge Distillation for Few-s...	2020-06-17	Code
18	FewTURE	88.9	No	Rethinking Generalization in Few-Shot Classifica...	2022-06-15	Code
19	MetaQDA	88.79	No	Shallow Bayesian Meta Learning for Real-World Fe...	2021-01-08	Code
20	MetaOptNet-SVM+Task Aug	88.38	No	Task Augmentation by Rotating for Meta-Learning	2020-02-08	Code
21	EASY 2xResNet12 1/√2 (inductive)	88.38	No	EASY: Ensemble Augmented-Shot Y-shaped Learning:...	2022-01-24	Code
22	R2-D2+Task Aug	88.33	No	Task Augmentation by Rotating for Meta-Learning	2020-02-08	Code
23	S2M2R	87.47	No	Charting the Right Manifold: Manifold Mixup for ...	2019-07-28	Code
24	Adaptive Subspace Network	87.3	No	-	-	Code
25	MCRNet-SVM	86.8	No	Complementing Representation Deficiency in Few-s...	2020-07-21	Code
26	ConstellationNets	86.8	No	-	-	Code
27	SSFormers	86.61	No	Sparse Spatial Transformers for Few-Shot Learning	2021-09-27	Code
28	RENet	86.6	No	Relational Embedding for Few-Shot Classification	2021-08-22	Code
29	SIB	85.3	No	Empirical Bayes Transductive Meta-Learning with ...	2020-04-27	Code
30	MCRNet-RR	85.2	No	Complementing Representation Deficiency in Few-s...	2020-07-21	Code
31	GML (ResNet-12)	85.08	No	Geometric Mean Improves Loss For Few-Shot Learning	2025-01-24	-
32	MetaOptNet-SVM-trainval	85	No	Meta-Learning with Differentiable Convex Optimiz...	2019-04-07	Code
33	ICI	84.32	No	Instance Credibility Inference for Few-Shot Lear...	2020-03-26	Code
34	Multi-Task Learning	84.1	No	Bridging Multi-Task Learning and Meta-Learning: ...	2021-06-16	Code
35	RCN - ResNet12	82.96	No	Region Comparison Network for Interpretable Few-...	2020-09-08	Code
36	MTUNet+WRN	82.93	No	Match Them Up: Visually Explainable Few-shot Ima...	2020-11-25	Code
37	MTUNet+ResNet-18	80.16	No	Match Them Up: Visually Explainable Few-shot Ima...	2020-11-25	Code
38	RCN - Conv4-64	77.63	No	Region Comparison Network for Interpretable Few-...	2020-09-08	Code
39	Relation Networks*	69.3	No	Learning to Compare: Relation Network for Few-Sh...	2017-11-16	Code

#1CAML [Laion-2b]SOTA
93.5
Accuracy· Extra Data· 2023-10-17
Context-Aware Meta-Learning Code
#2PT+MAP+SF+SOT (transductive)SOTA
92.83
Accuracy· 2022-04-06
The Self-Optimal-Transport Feature Transform Code
#3PT+MAP+SF+BPA (transductive)
92.83
Accuracy· 2024-06-25
The Balanced-Pairwise-Affinities Feature Transform Code
#4P>M>F (P=DINO-ViT-base, M=ProtoNet)
92.2
Accuracy· Extra Data· 2022-04-15
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference Code
#5PEMnE-BMS*SOTA
91.86
Accuracy· 2021-10-18
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning Code
#6Illumination AugmentationSOTA
91.09
Accuracy· 2021-02-06
Sill-Net: Feature Augmentation with Separated Illumination Representation Code
#7LST+MAP
90.73
Accuracy· 2021-02-09
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network Code
#8PT+MAPSOTA
90.68
Accuracy· 2020-06-06
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning Code
#9BAVARDAGE
90.63
Accuracy· 2022-09-18
Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification
#10HCTransformers
90.5
Accuracy· 2022-03-17
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning Code
#11EASY 3xResNet12 (transductive)
90.47
Accuracy· 2022-01-24
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Code
#12EASY 2xResNet12 1/√2 (transductive)
90.2
Accuracy· 2022-01-24
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Code
#13Invariance-Equivariance
89.74
Accuracy· 2021-03-01
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning Code
#14ACC + AmphibianSOTA
89.3
Accuracy· 2019-11-25
Generalized Adaptation for Few-Shot Learning
#15pseudo-shots
89.12
Accuracy· 2020-12-13
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks Code
#16EASY 3xResNet12 (inductive)
89
Accuracy· 2022-01-24
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Code
#17SKD
88.9
Accuracy· 2020-06-17
Self-supervised Knowledge Distillation for Few-shot Learning Code
#18FewTURE
88.9
Accuracy· 2022-06-15
Rethinking Generalization in Few-Shot Classification Code
#19MetaQDA
88.79
Accuracy· 2021-01-08
Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition Code
#20MetaOptNet-SVM+Task Aug
88.38
Accuracy· 2020-02-08
Task Augmentation by Rotating for Meta-Learning Code
#21EASY 2xResNet12 1/√2 (inductive)
88.38
Accuracy· 2022-01-24
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Code
#22R2-D2+Task Aug
88.33
Accuracy· 2020-02-08
Task Augmentation by Rotating for Meta-Learning Code
#23S2M2RSOTA
87.47
Accuracy· 2019-07-28
Charting the Right Manifold: Manifold Mixup for Few-shot Learning Code
#24Adaptive Subspace Network
87.3
Accuracy
No paperCode
#25MCRNet-SVM
86.8
Accuracy· 2020-07-21
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach Code
#26ConstellationNets
86.8
Accuracy
No paperCode
#27SSFormers
86.61
Accuracy· 2021-09-27
Sparse Spatial Transformers for Few-Shot Learning Code
#28RENet
86.6
Accuracy· 2021-08-22
Relational Embedding for Few-Shot Classification Code
#29SIB
85.3
Accuracy· 2020-04-27
Empirical Bayes Transductive Meta-Learning with Synthetic Gradients Code
#30MCRNet-RR
85.2
Accuracy· 2020-07-21
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach Code
#31GML (ResNet-12)
85.08
Accuracy· 2025-01-24
Geometric Mean Improves Loss For Few-Shot Learning
#32MetaOptNet-SVM-trainvalSOTA
85
Accuracy· 2019-04-07
Meta-Learning with Differentiable Convex Optimization Code
#33ICI
84.32
Accuracy· 2020-03-26
Instance Credibility Inference for Few-Shot Learning Code
#34Multi-Task Learning
84.1
Accuracy· 2021-06-16
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation Code
#35RCN - ResNet12
82.96
Accuracy· 2020-09-08
Region Comparison Network for Interpretable Few-shot Image Classification Code
#36MTUNet+WRN
82.93
Accuracy· 2020-11-25
Match Them Up: Visually Explainable Few-shot Image Classification Code
#37MTUNet+ResNet-18
80.16
Accuracy· 2020-11-25
Match Them Up: Visually Explainable Few-shot Image Classification Code
#38RCN - Conv4-64
77.63
Accuracy· 2020-09-08
Region Comparison Network for Interpretable Few-shot Image Classification Code
#39Relation Networks*SOTA
69.3
Accuracy· 2017-11-16
Learning to Compare: Relation Network for Few-Shot Learning Code