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

Showing 201250 of 3569 papers

TitleStatusHype
Learning Domain Invariant Prompt for Vision-Language ModelsCode1
Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive LearningCode1
Domain-General Crowd Counting in Unseen ScenariosCode1
Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation ModelsCode1
Multi-Modal Few-Shot Temporal Action DetectionCode1
Generalizable Implicit Neural Representations via Instance Pattern ComposersCode1
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision ResearchCode1
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot LearningCode1
Toward Unsupervised Outlier Model SelectionCode1
A picture of the space of typical learnable tasksCode1
Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback PathwaysCode1
m^4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-AdapterCode1
Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-RankingCode1
Continued Pretraining for Better Zero- and Few-Shot PromptabilityCode1
Meta-Learning via Classifier(-free) Diffusion GuidanceCode1
Few-shot Relational Reasoning via Connection Subgraph PretrainingCode1
Meta-Learning with Self-Improving Momentum TargetCode1
Stock Trading Volume Prediction with Dual-Process Meta-LearningCode1
CD-FSOD: A Benchmark for Cross-domain Few-shot Object DetectionCode1
Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-ExpertsCode1
DIMES: A Differentiable Meta Solver for Combinatorial Optimization ProblemsCode1
Learning to Learn and Sample BRDFsCode1
Hypernetwork approach to Bayesian MAMLCode1
Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-LearningCode1
MetaPrompting: Learning to Learn Better PromptsCode1
BOME! Bilevel Optimization Made Easy: A Simple First-Order ApproachCode1
Learning Symbolic Model-Agnostic Loss Functions via Meta-LearningCode1
Improving Fake News Detection of Influential Domain via Domain- and Instance-Level TransferCode1
Learning to Weight Samples for Dynamic Early-exiting NetworksCode1
MetaMask: Revisiting Dimensional Confounder for Self-Supervised LearningCode1
Difficulty-Net: Learning to Predict Difficulty for Long-Tailed RecognitionCode1
The Neural Process Family: Survey, Applications and PerspectivesCode1
Q-Net: Query-Informed Few-Shot Medical Image SegmentationCode1
Adversarial Feature Augmentation for Cross-domain Few-shot ClassificationCode1
Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive LearningCode1
Visual Localization via Few-Shot Scene Region ClassificationCode1
Learning to Generalize with Object-centric Agents in the Open World Survival Game CrafterCode1
Transformers as Meta-Learners for Implicit Neural RepresentationsCode1
Meta-Learning based Degradation Representation for Blind Super-ResolutionCode1
ArtFID: Quantitative Evaluation of Neural Style TransferCode1
Test-Time Adaptation via Conjugate Pseudo-labelsCode1
Tackling Long-Tailed Category Distribution Under Domain ShiftsCode1
Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning ApproachCode1
Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence ModelingCode1
A Large Scale Search Dataset for Unbiased Learning to RankCode1
On the Effectiveness of Sentence Encoding for Intent Detection Meta-LearningCode1
On the Generalizability and Predictability of Recommender SystemsCode1
MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot SegmentationCode1
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image ClassificationCode1
Zero-Shot AutoML with Pretrained ModelsCode1
Show:102550
← PrevPage 5 of 72Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8Unverified
2MZMeta-train success rate97.6Unverified
3MAMLMeta-test success rate36Unverified
4RL^2Meta-test success rate10Unverified
5DnCMeta-test success rate5.4Unverified
6PEARLMeta-test success rate0Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60Unverified
2Multi-task multi-head SACAverage Success Rate35.85Unverified
3DisCorAverage Success Rate26Unverified
4NDPAverage Success Rate11Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5Unverified
2MZMeta-test success rate (zero-shot)17.7Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75Unverified