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 1–10 of 2964 papers

TitleStatusHype
GLAD: Generalizable Tuning for Vision-Language Models—0
An Enhanced Privacy-preserving Federated Few-shot Learning Framework for Respiratory Disease Diagnosis—0
Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection—0
Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat TransportCode0
ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentation—0
Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications—0
Ancient Script Image Recognition and Processing: A Review—0
Universal Music Representations? Evaluating Foundation Models on World Music CorporaCode0
Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring—0
The Sample Complexity of Parameter-Free Stochastic Convex Optimization—0
Show:102550
← PrevPage 1 of 297Next →
All datasetsMedConceptsQADTDFGVC-AircraftMini-ImageNet - 5-Shot LearningMini-Imagenet 5-way (1-shot)Stanford CarsMini-ImageNet - 1-Shot LearningPubMedQACaltech101CaseHOLDEuroSATFlowers-102

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean81.12—Unverified