Image Classification on CUB 200 5-way 1-shot

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	PT+MAP+SF+SOT (transductive)	95.8	No	The Self-Optimal-Transport Feature Transform	2022-04-06	Code
2	CAML [Laion-2b]	95.8	Yes	Context-Aware Meta-Learning	2023-10-17	Code
3	PT+MAP+SF+BPA (transductive)	95.8	No	The Balanced-Pairwise-Affinities Feature Transform	2024-06-25	Code
4	PT+MAP+SF (transductive)	95.48	No	Few-Shot Learning by Integrating Spatial and Fre...	2021-05-11	Code
5	PEMnE-BMS*	94.78	Yes	Squeezing Backbone Feature Distributions to the ...	2021-10-18	Code
6	Illumination Augmentation	94.73	No	Sill-Net: Feature Augmentation with Separated Il...	2021-02-06	Code
7	LST+MAP	91.68	No	Transfer learning based few-shot classification ...	2021-02-09	Code
8	EASY 3xResNet12 (transductive)	90.56	No	EASY: Ensemble Augmented-Shot Y-shaped Learning:...	2022-01-24	Code
9	EASY 4xResNet12 (transductive)	90.5	No	EASY: Ensemble Augmented-Shot Y-shaped Learning:...	2022-01-24	Code
10	BAVARDAGE	90.42	No	Adaptive Dimension Reduction and Variational Inf...	2022-09-18	-
11	ICI	89.58	No	Instance Credibility Inference for Few-Shot Lear...	2020-03-26	Code
12	ESPT	85.45	No	ESPT: A Self-Supervised Episodic Spatial Pretext...	2023-04-26	Code
13	TDM	84.36	No	Task Discrepancy Maximization for Fine-grained F...	2022-07-04	Code
14	BD-CSPN + ESFR (ResNet-18)	82.68	No	Unsupervised Embedding Adaptation via Early-Stag...	2021-06-22	Code
15	LaplacianShot	80.96	No	Laplacian Regularized Few-Shot Learning	2020-06-28	Code
16	S2M2R	80.68	No	Charting the Right Manifold: Manifold Mixup for ...	2019-07-28	Code
17	RENet	79.49	No	Relational Embedding for Few-Shot Classification	2021-08-22	Code
18	Ours	79.12	No	Variational Feature Disentangling for Fine-Grain...	2020-10-07	-
19	EASY 3xResNet12 (inductive)	78.56	No	EASY: Ensemble Augmented-Shot Y-shaped Learning:...	2022-01-24	Code
20	EASY 4xResNet12 (inductive)	77.97	No	EASY: Ensemble Augmented-Shot Y-shaped Learning:...	2022-01-24	Code
21	AmdimNet	77.09	No	Self-Supervised Learning For Few-Shot Image Clas...	2019-11-14	Code
22	MergedNet-Max	75.34	No	-	-	Code
23	Neg-Margin	72.66	No	Negative Margin Matters: Understanding Margin in...	2020-03-26	Code
24	DKT + BNCosSim	72.27	No	Bayesian Meta-Learning for the Few-Shot Setting ...	2019-10-11	Code
25	Self-Critique and Adapt + High-End MAML++	70.46	No	Learning to learn via Self-Critique	2019-05-24	Code
26	Delta-encoder	69.8	No	Delta-encoder: an effective sample synthesis met...	2018-06-12	Code
27	feat (ProtoNet)	68.65	No	Few-Shot Learning via Embedding Adaptation with ...	2018-12-10	Code
28	High-End MAML++	67.48	No	Learning to learn via Self-Critique	2019-05-24	Code
29	HyperShot	66.13	No	HyperShot: Few-Shot Learning by Kernel HyperNetw...	2022-03-21	Code
30	RS-FSL	65.66	Yes	Rich Semantics Improve Few-shot Learning	2021-04-26	-
31	Hyperbolic ProtoNet	60.52	No	Hyperbolic Image Embeddings	2019-04-03	Code
32	DN4-DA (k=1)	53.15	No	Revisiting Local Descriptor based Image-to-Class...	2019-03-28	Code
33	Relation Net	50.44	No	Learning to Compare: Relation Network for Few-Sh...	2017-11-16	Code

#1PT+MAP+SF+SOT (transductive)SOTA
95.8
Accuracy· 2022-04-06
The Self-Optimal-Transport Feature Transform Code
#2CAML [Laion-2b]
95.8
Accuracy· Extra Data· 2023-10-17
Context-Aware Meta-Learning Code
#3PT+MAP+SF+BPA (transductive)
95.8
Accuracy· 2024-06-25
The Balanced-Pairwise-Affinities Feature Transform Code
#4PT+MAP+SF (transductive)SOTA
95.48
Accuracy· 2021-05-11
Few-Shot Learning by Integrating Spatial and Frequency Representation Code
#5PEMnE-BMS*
94.78
Accuracy· Extra Data· 2021-10-18
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning Code
#6Illumination AugmentationSOTA
94.73
Accuracy· 2021-02-06
Sill-Net: Feature Augmentation with Separated Illumination Representation Code
#7LST+MAP
91.68
Accuracy· 2021-02-09
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network Code
#8EASY 3xResNet12 (transductive)
90.56
Accuracy· 2022-01-24
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Code
#9EASY 4xResNet12 (transductive)
90.5
Accuracy· 2022-01-24
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Code
#10BAVARDAGE
90.42
Accuracy· 2022-09-18
Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification
#11ICISOTA
89.58
Accuracy· 2020-03-26
Instance Credibility Inference for Few-Shot Learning Code
#12ESPT
85.45
Accuracy· 2023-04-26
ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning Code
#13TDM
84.36
Accuracy· 2022-07-04
Task Discrepancy Maximization for Fine-grained Few-Shot Classification Code
#14BD-CSPN + ESFR (ResNet-18)
82.68
Accuracy· 2021-06-22
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification Code
#15LaplacianShot
80.96
Accuracy· 2020-06-28
Laplacian Regularized Few-Shot Learning Code
#16S2M2RSOTA
80.68
Accuracy· 2019-07-28
Charting the Right Manifold: Manifold Mixup for Few-shot Learning Code
#17RENet
79.49
Accuracy· 2021-08-22
Relational Embedding for Few-Shot Classification Code
#18Ours
79.12
Accuracy· 2020-10-07
Variational Feature Disentangling for Fine-Grained Few-Shot Classification
#19EASY 3xResNet12 (inductive)
78.56
Accuracy· 2022-01-24
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Code
#20EASY 4xResNet12 (inductive)
77.97
Accuracy· 2022-01-24
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Code
#21AmdimNet
77.09
Accuracy· 2019-11-14
Self-Supervised Learning For Few-Shot Image Classification Code
#22MergedNet-Max
75.34
Accuracy
No paperCode
#23Neg-Margin
72.66
Accuracy· 2020-03-26
Negative Margin Matters: Understanding Margin in Few-shot Classification Code
#24DKT + BNCosSim
72.27
Accuracy· 2019-10-11
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels Code
#25Self-Critique and Adapt + High-End MAML++SOTA
70.46
Accuracy· 2019-05-24
Learning to learn via Self-Critique Code
#26Delta-encoderSOTA
69.8
Accuracy· 2018-06-12
Delta-encoder: an effective sample synthesis method for few-shot object recognition Code
#27feat (ProtoNet)
68.65
Accuracy· 2018-12-10
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions Code
#28High-End MAML++
67.48
Accuracy· 2019-05-24
Learning to learn via Self-Critique Code
#29HyperShot
66.13
Accuracy· 2022-03-21
HyperShot: Few-Shot Learning by Kernel HyperNetworks Code
#30RS-FSL
65.66
Accuracy· Extra Data· 2021-04-26
Rich Semantics Improve Few-shot Learning
#31Hyperbolic ProtoNet
60.52
Accuracy· 2019-04-03
Hyperbolic Image Embeddings Code
#32DN4-DA (k=1)
53.15
Accuracy· 2019-03-28
Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning Code
#33Relation NetSOTA
50.44
Accuracy· 2017-11-16
Learning to Compare: Relation Network for Few-Shot Learning Code