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 2941–2950 of 3569 papers

TitleStatusHype
Learning to Learn Cropping Models for Different Aspect Ratio RequirementsCode0
Deep Metric Learning via Adaptive Learnable Assessment—0
Online Depth Learning Against Forgetting in Monocular Videos—0
When Does MAML Objective Have Benign Landscape?—0
MetaInv-Net: Meta Inversion Network for Sparse View CT Image Reconstruction—0
High-order structure preserving graph neural network for few-shot learningCode0
Algorithm Selection Framework for Cyber Attack Detection—0
Boosting Few-Shot Learning With Adaptive Margin Loss—0
Looking back to lower-level information in few-shot learning—0
Towards intervention-centric causal reasoning in learning agents—0
Show:102550
← PrevPage 295 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