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 1601–1650 of 3569 papers

TitleStatusHype
Learning to Adapt to Domain Shifts with Few-shot Samples in Anomalous Sound Detection—0
Model Based Meta Learning of Critics for Policy Gradients—0
Towards Explainable Meta-Learning for DDoS Detection—0
Disentangling Abstraction from Statistical Pattern Matching in Human and Machine LearningCode0
Context-aware Visual Tracking with Joint Meta-updating—0
Meta-Learning Approaches for a One-Shot Collective-Decision Aggregation: Correctly Choosing how to Choose Correctly—0
A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations—0
AutoProtoNet: Interpretability for Prototypical NetworksCode0
Scalable Semi-Modular Inference with Variational Meta-PosteriorsCode0
On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting—0
Diverse Preference Augmentation with Multiple Domains for Cold-start RecommendationsCode0
Quantum-Aided Meta-Learning for Bayesian Binary Neural Networks via Born Machines—0
Improved Relation Networks for End-to-End Speaker Verification and Identification—0
Few-Shot Class-Incremental Learning by Sampling Multi-Phase TasksCode1
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations—0
Higher-Order Generalization Bounds: Learning Deep Probabilistic Programs via PAC-Bayes Objectives—0
Supervised Graph Contrastive Learning for Few-shot Node Classification—0
Exploring Frequency Adversarial Attacks for Face Forgery Detection—0
Zero-shot meta-learning for small-scale data from human subjects—0
Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks—0
Boosting Black-Box Adversarial Attacks with Meta Learning—0
Sketch3T: Test-Time Training for Zero-Shot SBIR—0
Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task DivisionCode0
Style-Guided Domain Adaptation for Face Presentation Attack Detection—0
A Framework of Meta Functional Learning for Regularising Knowledge Transfer—0
Temporal Transductive Inference for Few-Shot Video Object SegmentationCode0
Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison—0
Learn to Adapt for Monocular Depth Estimation—0
CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification—0
Learning to Adapt to Unseen Abnormal Activities under Weak SupervisionCode1
Cross-Domain Few-Shot Semantic SegmentationCode1
Predicting Multi-Antenna Frequency-Selective Channels via Meta-Learned Linear Filters based on Long-Short Term Channel DecompositionCode1
Pre-training to Match for Unified Low-shot Relation ExtractionCode1
Multidimensional Belief Quantification for Label-Efficient Meta-LearningCode0
Domain-Generalized Textured Surface Anomaly Detection—0
Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation—0
Meta-X_NLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and GenerationCode0
Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-LearningCode0
Meta-Learning for Online Update of Recommender SystemsCode0
Negative Inner-Loop Learning Rates Learn Universal Features—0
Meta-Reinforcement Learning for the Tuning of PI Controllers: An Offline Approach—0
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot LearningCode1
Meta-Learning of NAS for Few-shot Learning in Medical Image Applications—0
Practical Conditional Neural Processes Via Tractable Dependent Predictions—0
Learning What Not to Segment: A New Perspective on Few-Shot SegmentationCode2
Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels—0
Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition—0
MetAug: Contrastive Learning via Meta Feature AugmentationCode1
SuperCone: Unified User Segmentation over Heterogeneous Experts via Concept Meta-learning—0
What Matters For Meta-Learning Vision Regression Tasks?Code1
Show:102550
← PrevPage 33 of 72Next →
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