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 301–325 of 2964 papers

Title	Date	Tasks	Status	Hype
EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder	Dec 8, 2022	Few-Shot LearningSegmentation	CodeCode Available	1
Finetune like you pretrain: Improved finetuning of zero-shot vision models	Dec 1, 2022	DescriptiveFew-Shot Learning	CodeCode Available	1
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification	Nov 30, 2022	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available	1
Better Generalized Few-Shot Learning Even Without Base Data	Nov 29, 2022	Few-Shot LearningGeneralized Few-Shot Learning	CodeCode Available	1
RankDNN: Learning to Rank for Few-shot Learning	Nov 28, 2022	Few-Shot Learningimage-classification	CodeCode Available	1
TEMPERA: Test-Time Prompting via Reinforcement Learning	Nov 21, 2022	Few-Shot LearningNatural Language Inference	CodeCode Available	1
QAmeleon: Multilingual QA with Only 5 Examples	Nov 15, 2022	Few-Shot LearningQuestion Answering	CodeCode Available	1
Retrieval-Augmented Generative Question Answering for Event Argument Extraction	Nov 14, 2022	Event Argument ExtractionFew-Shot Learning	CodeCode Available	1
AdaptKeyBERT: An Attention-Based approach towards Few-Shot & Zero-Shot Domain Adaptation of KeyBERT	Nov 14, 2022	Domain AdaptationFact Verification	CodeCode Available	1
Enhancing Few-shot Image Classification with Cosine Transformer	Nov 13, 2022	ClassificationFew-Shot Image Classification	CodeCode Available	1
Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning	Nov 13, 2022	3D Object DetectionDecoder	CodeCode Available	1
miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings	Nov 9, 2022	Contrastive LearningFew-Shot Learning	CodeCode Available	1
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning	Nov 6, 2022	Few-Shot LearningMeta-Learning	CodeCode Available	1
Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid	Oct 30, 2022	Few-Shot LearningSelection bias	CodeCode Available	1
Better Few-Shot Relation Extraction with Label Prompt Dropout	Oct 25, 2022	Few-Shot LearningRelation	CodeCode Available	1
Contrastive Prototypical Network with Wasserstein Confidence Penalty	Oct 21, 2022	Contrastive LearningFew-Shot Learning	CodeCode Available	1
Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus	Oct 18, 2022	ARCBenchmarking	CodeCode Available	1
RARR: Researching and Revising What Language Models Say, Using Language Models	Oct 17, 2022	Few-Shot LearningLanguage Modeling	CodeCode Available	1
Meta-Learning via Classifier(-free) Diffusion Guidance	Oct 17, 2022	Few-Shot LearningImage Generation	CodeCode Available	1
Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning	Oct 14, 2022	Few-Shot LearningMachine Reading Comprehension	CodeCode Available	1
Unified Vision and Language Prompt Learning	Oct 13, 2022	Domain GeneralizationFew-Shot Learning	CodeCode Available	1
Self-Attention Message Passing for Contrastive Few-Shot Learning	Oct 12, 2022	Contrastive LearningFew-Shot Learning	CodeCode Available	1
Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis	Oct 12, 2022	Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)	CodeCode Available	1
ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning	Oct 11, 2022	Cross-Domain Few-Shotcross-domain few-shot learning	CodeCode Available	1
Hypernetwork approach to Bayesian MAML	Oct 6, 2022	Few-Shot LearningMeta-Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 13 of 119Next →

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	gpt-4-0125-preview	Accuracy	61.91	—	Unverified
2	gpt-4-0125-preview	Accuracy	52.49	—	Unverified
3	gpt-3.5-turbo	Accuracy	41.48	—	Unverified
4	gpt-3.5-turbo	Accuracy	37.06	—	Unverified
5	johnsnowlabs/JSL-MedMNX-7B	Accuracy	25.63	—	Unverified
6	yikuan8/Clinical-Longformer	Accuracy	25.55	—	Unverified
7	BioMistral/BioMistral-7B-DARE	Accuracy	25.06	—	Unverified
8	yikuan8/Clinical-Longformer	Accuracy	25.04	—	Unverified
9	PharMolix/BioMedGPT-LM-7B	Accuracy	24.92	—	Unverified
10	PharMolix/BioMedGPT-LM-7B	Accuracy	24.75	—	Unverified

#	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

#	Model	Metric	Claimed	Verified	Status
1	SaSPA + CAL	Harmonic mean	52.2	—	Unverified
2	CAL	Harmonic mean	35.2	—	Unverified
3	Variational Prompt Tuning	Harmonic mean	34.69	—	Unverified
4	Real-Guidance + CAL	Harmonic mean	34.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BGNN	Accuracy	92.7	—	Unverified
2	TIM-GD	Accuracy	87.4	—	Unverified
3	UNEM-Gaussian	Accuracy	66.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	EASY (transductive)	Accuracy	82.75	—	Unverified
2	HCTransformers	5 way 1~2 shot	74.74	—	Unverified
3	HyperShot	Accuracy	53.18	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SaSPA + CAL	4-shot Accuracy	66.7	—	Unverified
2	Real-Guidance + CAL	4-shot Accuracy	44.3	—	Unverified
3	CAL	4-shot Accuracy	42.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HCTransformers	Acc	74.74	—	Unverified
2	DPGN	Acc	67.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MetaGen Blended RAG (zero-shot)	Accuracy	77.9	—	Unverified
2	CoT-T5-11B (1024 Shot)	Accuracy	73.42	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	96.44	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CoT-T5-11B (1024 Shot)	Accuracy	68.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	77.71	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	81.12	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	91.57	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CovidExpert	AUC-ROC	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CoT-T5-11B (1024 Shot)	Accuracy	78.02	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UNEM-Gaussian	Accuracy	65.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UNEM-Gaussian	Accuracy	73.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	96.82	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	73.07	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	78.51	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UNEM-Gaussian	Accuracy	52.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Variational Prompt Tuning	Harmonic mean	79	—	Unverified