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 3031–3040 of 3569 papers

TitleStatusHype
Learning to Learn without Forgetting using AttentionCode0
CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy LabelsCode0
Latent Representation Learning of Multi-scale Thermophysics: Application to Dynamics in Shocked Porous Energetic MaterialCode0
Associative Alignment for Few-shot Image ClassificationCode0
MetaAug: Meta-Data Augmentation for Post-Training QuantizationCode0
Classical Sequence Match is a Competitive Few-Shot One-Class LearnerCode0
Reinforcement Learning for Few-Shot Text Generation AdaptationCode0
Rethinking Task Sampling for Few-shot Vision-Language Transfer LearningCode0
Latent-Optimized Adversarial Neural Transfer for Sarcasm DetectionCode0
Reinforcement Learning In Two Player Zero Sum Simultaneous Action GamesCode0
Show:102550
← PrevPage 304 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