paper-with-me

Few-Shot Image Classification 벤치마크

Few-Shot Image Classification on OMNIGLOT - 1-Shot, 20-way

40개 결과 · ⬇ CSV · JSON

Accuracy

83.3 87.38 91.47 95.55 99.63 2016-06 2026-09 Neural Statistician — 93.2 (2016-06-07) Neural Statistician — 93.2 (2016-06-07) Matching Nets — 93.8 (2016-06-13) Matching Nets — 93.8 (2016-06-13) ConvNet with Memory Module — 95.0 (2017-03-09) ConvNet with Memory Module — 95.0 (2017-03-09) Prototypical Networks — 96.0 (2017-03-15) Prototypical Networks — 96.0 (2017-03-15) Relation Net — 97.6 (2017-11-16) Relation Net — 97.6 (2017-11-16) adaCNN (DF) — 96.12 (2017-12-28) adaCNN (DF) — 96.12 (2017-12-28) MT-net — 96.2 (2018-01-17) MT-net — 96.2 (2018-01-17) Reptile + Transduction — 89.43 (2018-03-08) Reptile + Transduction — 89.43 (2018-03-08) MAML++ — 97.65 (2018-10-22) MAML++ — 97.65 (2018-10-22) APL — 97.2 (2019-02-07) APL — 97.2 (2019-02-07) MC2+ — 88.0 (2019-02-09) MC2+ — 88.0 (2019-02-09) Hyperbolic ProtoNet — 95.9 (2019-04-03) Hyperbolic ProtoNet — 95.9 (2019-04-03) TapNet — 98.07 (2019-05-16) TapNet — 98.07 (2019-05-16) VAMPIRE — 93.2 (2019-07-27) VAMPIRE — 93.2 (2019-07-27) GCR — 99.63 (2019-08-14) GCR — 99.63 (2019-08-14) iMAML, Hessian-Free — 96.18 (2019-09-10) iMAML, Hessian-Free — 96.18 (2019-09-10) DCN6-E — 99.11 (2019-09-25) DCN4 — 98.8 (2019-09-25) DCN6-E — 99.11 (2019-09-25) DCN4 — 98.8 (2019-09-25) MR-MAML — 83.3 (2019-12-09) MR-MAML — 83.3 (2019-12-09) MAML++ — 97.7 (2022-01-11) MAML++ — 97.7 (2022-01-11) Neural Statistician — 93.2 (2016-06-07) Matching Nets — 93.8 (2016-06-13) ConvNet with Memory Module — 95.0 (2017-03-09) Prototypical Networks — 96.0 (2017-03-15) Relation Net — 97.6 (2017-11-16) MAML++ — 97.65 (2018-10-22) TapNet — 98.07 (2019-05-16) GCR — 99.63 (2019-08-14)
RankModel Accuracy PaperCodeYear
1 GCR 99.63 Few-Shot Learning with Global Class Representations tiangeluo/fsl-global · huang-research-group/globalfsl2019 2019
2 DCN6-E 99.11 Decoder Choice Network for Meta-Learning AceChuse/DCN 2019
3 DCN4 98.8% Decoder Choice Network for Meta-Learning AceChuse/DCN 2019
4 TapNet 98.07% TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning istarjun/TapNet 2019
5 MAML++ 97.7 HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning google-research/google-research · shyamsn97/hyper-nn 2022
6 MAML++ 97.65 How to train your MAML AntreasAntoniou/HowToTrainYourMAMLPytorch · JWSoh/MZSR · Tikquuss/meta_XLM · +7 2018
7 Relation Net 97.6% Learning to Compare: Relation Network for Few-Shot Learning sicara/easy-few-shot-learning · floodsung/LearningToCompare_FSL · lzrobots/LearningToCompare_ZSL · +10 2017
8 APL 97.2% Adaptive Posterior Learning: few-shot learning with a surprise-based memory module cogentlabs/apl 2019
9 MT-net 96.2% Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace yoonholee/MT-net 2018
10 iMAML, Hessian-Free 96.18 Meta-Learning with Implicit Gradients prolearner/hypertorch · prolearner/hypergrad · dbaranchuk/memory-efficient-maml · +3 2019
11 adaCNN (DF) 96.12% Rapid Adaptation with Conditionally Shifted Neurons 2017
12 Prototypical Networks 96% Prototypical Networks for Few-shot Learning learnables/learn2learn · oscarknagg/few-shot · sicara/easy-few-shot-learning · +40 2017
13 Hyperbolic ProtoNet 95.9% Hyperbolic Image Embeddings KhrulkovV/hyperbolic-image-embeddings · leymir/hyperbolic-image-embeddings · nalexai/hyperlib 2019
14 ConvNet with Memory Module 95% Learning to Remember Rare Events tensorflow/models · rdspring1/lsh_deeplearning 2017
15 Matching Nets 93.8% Matching Networks for One Shot Learning oscarknagg/few-shot · sicara/easy-few-shot-learning · Sha-Lab/FEAT · +23 2016
16 Neural Statistician 93.2% Towards a Neural Statistician conormdurkan/neural-statistician · lupalab/flowscan · comramona/neural-statistician · +2 2016
16 VAMPIRE 93.2 Uncertainty in Model-Agnostic Meta-Learning using Variational Inference cnguyen10/few_shot_meta_learning 2019
18 Reptile + Transduction 89.43% On First-Order Meta-Learning Algorithms learnables/learn2learn · MaximeVandegar/Papers-in-100-Lines-of-Code · openai/supervised-reptile · +10 2018
19 MC2+ 88% Meta-Curvature silverbottlep/meta_curvature 2019
20 MR-MAML 83.3 Meta-Learning without Memorization google-research/google-research 2019
1–20 / 40 다음 → 페이지당 10 20 50 100