SOTAVerified

Meta-Learning

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 561–570 of 3569 papers

TitleStatusHype
Deep Random Projector: Accelerated Deep Image PriorCode1
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot LearnersCode1
Few Shot Dialogue State Tracking using Meta-learningCode1
Consistency-guided Meta-Learning for Bootstrapping Semi-Supervised Medical Image SegmentationCode1
m^4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-AdapterCode1
MAML is a Noisy Contrastive Learner in ClassificationCode1
Depth Guided Adaptive Meta-Fusion Network for Few-shot Video RecognitionCode1
Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object DetectionCode1
MC-BERT: Efficient Language Pre-Training via a Meta ControllerCode1
Can Learned Optimization Make Reinforcement Learning Less Difficult?Code1
Show:102550
← PrevPage 57 of 357Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified