SOTAVerified

Few-Shot Learning

Few-Shot Learning is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation.

Source: Penalty Method for Inversion-Free Deep Bilevel Optimization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1851–1900 of 2964 papers

TitleStatusHype
A MIMO Radar-Based Metric Learning Approach for Activity Recognition—0
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP—0
Few-Shot Named Entity Recognition: An Empirical Baseline Study—0
Learning Prototype Representations Across Few-Shot Tasks for Event DetectionCode0
TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text ClassificationCode1
Towards Realistic Few-Shot Relation ExtractionCode1
Continual Few-Shot Learning for Text ClassificationCode0
Data-Efficient Language Shaped Few-shot Image ClassificationCode0
Influential Prototypical Networks for Few Shot Learning: A Dermatological Case Study—0
Few-shot learning with improved local representations via bias rectify module—0
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat MinimaCode1
MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning—0
MetaICL: Learning to Learn In ContextCode1
Domain Agnostic Few-Shot Learning For Document Intelligence—0
Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D PoseCode1
On sensitivity of meta-learning to support dataCode1
Non-Gaussian Gaussian Processes for Few-Shot RegressionCode1
Self-Denoising Neural Networks for Few Shot Learning—0
Task-Aware Meta Learning-based Siamese Neural Network for Classifying Obfuscated Malware—0
Meta-Learning for Multi-Label Few-Shot Classification—0
Instant Response Few-shot Object Detection with Meta Strategy and Explicit Localization InferenceCode0
Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-LearningCode0
MaskSplit: Self-supervised Meta-learning for Few-shot Semantic SegmentationCode1
SCHA-VAE: Hierarchical Context Aggregation for Few-Shot GenerationCode1
GCCN: Global Context Convolutional Network—0
A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning—0
Contextual Gradient Scaling for Few-Shot LearningCode0
On Label-Efficient Computer Vision: Building Fast and Effective Few-Shot Image Classifiers—0
Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning—0
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot LearningCode1
PPT: Pre-trained Prompt Tuning for Few-shot Learning—0
Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning—0
Few-Shot Learning with Siamese Networks and Label Tuning—0
A MIMO Radar-based Few-Shot Learning Approach for Human-ID—0
HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model CompressionCode0
Hyperseed: Unsupervised Learning with Vector Symbolic ArchitecturesCode1
Few-Shot Bot: Prompt-Based Learning for Dialogue SystemsCode1
Can Explanations Be Useful for Calibrating Black Box Models?Code1
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning—0
LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5Code1
Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning—0
Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers—0
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot LearnersCode1
Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLICode0
A Closer Look at Prototype Classifier for Few-shot Image Classification—0
Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot LearningCode1
Injecting Text and Cross-lingual Supervision in Few-shot Learning from Self-Supervised Models—0
Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease ClassificationCode0
Meta-Learning with Task-Adaptive Loss Function for Few-Shot LearningCode1
Sparse MoEs meet Efficient EnsemblesCode1
Show:102550
← PrevPage 38 of 60Next →
All datasetsMedConceptsQADTDFGVC-AircraftMini-ImageNet - 5-Shot LearningMini-Imagenet 5-way (1-shot)Stanford CarsMini-ImageNet - 1-Shot LearningPubMedQACaltech101CaseHOLDEuroSATFlowers-102

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1gpt-4-0125-previewAccuracy61.91—Unverified
2gpt-4-0125-previewAccuracy52.49—Unverified
3gpt-3.5-turboAccuracy41.48—Unverified
4gpt-3.5-turboAccuracy37.06—Unverified
5johnsnowlabs/JSL-MedMNX-7BAccuracy25.63—Unverified
6yikuan8/Clinical-LongformerAccuracy25.55—Unverified
7BioMistral/BioMistral-7B-DAREAccuracy25.06—Unverified
8yikuan8/Clinical-LongformerAccuracy25.04—Unverified
9PharMolix/BioMedGPT-LM-7BAccuracy24.92—Unverified
10PharMolix/BioMedGPT-LM-7BAccuracy24.75—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean67.27—Unverified
2SaSPA + CAL4-shot Accuracy48.3—Unverified
3Real-Guidance + CAL4-shot Accuracy41.5—Unverified
4CAL4-shot Accuracy40.9—Unverified
#ModelMetricClaimedVerifiedStatus
1SaSPA + CALHarmonic mean52.2—Unverified
2CALHarmonic mean35.2—Unverified
3Variational Prompt TuningHarmonic mean34.69—Unverified
4Real-Guidance + CALHarmonic mean34.5—Unverified
#ModelMetricClaimedVerifiedStatus
1BGNNAccuracy92.7—Unverified
2TIM-GDAccuracy87.4—Unverified
3UNEM-GaussianAccuracy66.4—Unverified
#ModelMetricClaimedVerifiedStatus
1EASY (transductive)Accuracy82.75—Unverified
2HCTransformers5 way 1~2 shot74.74—Unverified
3HyperShotAccuracy53.18—Unverified
#ModelMetricClaimedVerifiedStatus
1SaSPA + CAL4-shot Accuracy66.7—Unverified
2Real-Guidance + CAL4-shot Accuracy44.3—Unverified
3CAL4-shot Accuracy42.2—Unverified
#ModelMetricClaimedVerifiedStatus
1HCTransformersAcc74.74—Unverified
2DPGNAcc67.6—Unverified
#ModelMetricClaimedVerifiedStatus
1MetaGen Blended RAG (zero-shot)Accuracy77.9—Unverified
2CoT-T5-11B (1024 Shot)Accuracy73.42—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean96.44—Unverified
#ModelMetricClaimedVerifiedStatus
1CoT-T5-11B (1024 Shot)Accuracy68.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean77.71—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean81.12—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean91.57—Unverified
#ModelMetricClaimedVerifiedStatus
1CovidExpertAUC-ROC1—Unverified
#ModelMetricClaimedVerifiedStatus
1CoT-T5-11B (1024 Shot)Accuracy78.02—Unverified
#ModelMetricClaimedVerifiedStatus
1UNEM-GaussianAccuracy65.7—Unverified
#ModelMetricClaimedVerifiedStatus
1UNEM-GaussianAccuracy73.2—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean96.82—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean73.07—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean78.51—Unverified
#ModelMetricClaimedVerifiedStatus
1UNEM-GaussianAccuracy52.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean79—Unverified