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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 2964 papers

Title	Date	Tasks	Status
GLAD: Generalizable Tuning for Vision-Language Models	Jul 17, 2025	Domain GeneralizationFew-Shot Learning	—Unverified
An Enhanced Privacy-preserving Federated Few-shot Learning Framework for Respiratory Disease Diagnosis	Jul 10, 2025	DiagnosticFew-Shot Learning	—Unverified
Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection	Jul 10, 2025	Domain AdaptationFew-Shot Learning	—Unverified
Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport	Jul 8, 2025	Few-Shot Learning	CodeCode Available
ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentation	Jul 3, 2025	Few-Shot LearningSegmentation	—Unverified
Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications	Jun 25, 2025	Few-Shot Learning	—Unverified
Ancient Script Image Recognition and Processing: A Review	Jun 24, 2025	DeciphermentFew-Shot Learning	—Unverified
Universal Music Representations? Evaluating Foundation Models on World Music Corpora	Jun 20, 2025	BenchmarkingFew-Shot Learning	CodeCode Available
Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring	Jun 16, 2025	BenchmarkingFew-Shot Learning	—Unverified
The Sample Complexity of Parameter-Free Stochastic Convex Optimization	Jun 12, 2025	Few-Shot LearningModel Selection	—Unverified

Show:10 25 50

← PrevPage 1 of 297Next →

All datasets MedConceptsQA DTD FGVC-Aircraft Mini-ImageNet - 5-Shot Learning Mini-Imagenet 5-way (1-shot)Stanford Cars Mini-ImageNet - 1-Shot Learning PubMedQA Caltech101 CaseHOLD EuroSAT Flowers-102

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	67.27	—	Unverified
2	SaSPA + CAL	4-shot Accuracy	48.3	—	Unverified
3	Real-Guidance + CAL	4-shot Accuracy	41.5	—	Unverified
4	CAL	4-shot Accuracy	40.9	—	Unverified