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 1426–1450 of 3569 papers

TitleStatusHype
Exploring Graph Classification Techniques Under Low Data Constraints: A Comprehensive Study—0
Exploring Frequency Adversarial Attacks for Face Forgery Detection—0
Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection—0
An Adaptive Approach for Probabilistic Wind Power Forecasting Based on Meta-Learning—0
A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation—0
Adaptive Task Sampling for Meta-Learning—0
Brain-inspired global-local learning incorporated with neuromorphic computing—0
Exploring Domain Shift in Extractive Text Summarization—0
BP-DeepONet: A new method for cuffless blood pressure estimation using the physcis-informed DeepONet—0
Amsqr at SemEval-2022 Task 4: Towards AutoNLP via Meta-Learning and Adversarial Data Augmentation for PCL Detection—0
Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling—0
Amortized Proximal Optimization—0
Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology—0
Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning—0
Boosting Natural Language Generation from Instructions with Meta-Learning—0
Boosting Model Resilience via Implicit Adversarial Data Augmentation—0
Boosting Meta-Training with Base Class Information for Few-Shot Learning—0
Amortized Bayesian Meta-Learning—0
Adaptive Submodular Meta-Learning—0
A Primal-Dual Approach to Bilevel Optimization with Multiple Inner Minima—0
Explaining the Performance of Multi-label Classification Methods with Data Set Properties—0
Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification—0
Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization—0
Amortised Inference in Neural Networks for Small-Scale Probabilistic Meta-Learning—0
Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classification—0
Show:102550
← PrevPage 58 of 143Next →
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