Papers with Code 아카이브

Few-Shot Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 12
평가표: 27
보존된 평가 기록: 52

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/jim-schwoebel/allie

Ludwig: a type-based declarative deep learning toolbox

https://github.com/jnhwkim/cbp

Compact Bilinear Pooling

https://github.com/joe-siyuan-qiao/FewShot-CVPR

Few-Shot Image Recognition by Predicting Parameters from Activations

https://github.com/johswald/learning_where_to_learn

BOIL: Towards Representation Change for Few-shot Learning

https://github.com/jonasrothfuss/promp

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

https://github.com/joshfp/fellowship.ai

Prototypical Networks for Few-shot Learning

https://github.com/joshfp/one-shot-learning

Prototypical Networks for Few-shot Learning

https://github.com/jpablou/Matching-The-Blanks-Ths

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

https://github.com/jsalbert/prototypical-networks

Prototypical Networks for Few-shot Learning

https://github.com/juletx/lm-evaluation-harness

Language Models are Few-Shot Learners

https://github.com/jxbz/agd

Feature Learning in Infinite-Width Neural Networks

https://github.com/kaize0409/GPN_Graph-Few-shot

Graph Prototypical Networks for Few-shot Learning on Attributed Networks

https://github.com/kaize0409/meta-gdn

Few-shot Network Anomaly Detection via Cross-network Meta-learning

https://github.com/kakaobrain/kogpt

What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers

https://github.com/kakaoenterprise/kakaoenterprise.github.io

A Plug-in Method for Representation Factorization in Connectionist Models

https://github.com/karl-hajjar/wide-networks

Feature Learning in Infinite-Width Neural Networks

https://github.com/karpathy/build-nanogpt

Language Models are Few-Shot Learners

https://github.com/karpathy/llm.c

Language Models are Few-Shot Learners

https://github.com/katerakelly/pytorch-maml

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

https://github.com/kayvr/token-hawk

LLaMA: Open and Efficient Foundation Language Models

https://github.com/kbressem/medalpaca

LLaMA: Open and Efficient Foundation Language Models

https://github.com/keanson/revisit-logistic-softmax

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

https://github.com/keonlee9420/Daft-Exprt

TADAM: Task dependent adaptive metric for improved few-shot learning

https://github.com/khoiucd/LearningToCompare-Tensorflow

Learning to Compare: Relation Network for Few-Shot Learning

https://github.com/kieranjwood/trading-momentum-transformer

Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies

https://github.com/kipgparker/soft-prompt-tuning

The Power of Scale for Parameter-Efficient Prompt Tuning

https://github.com/knnaraghi/fewshot

Matching Networks for One Shot Learning

https://github.com/krafton-ai/korani

LLaMA: Open and Efficient Foundation Language Models

https://github.com/kridgeway/f-statistic-loss-nips-2018

Learning Deep Disentangled Embeddings with the F-Statistic Loss

https://github.com/kuldeep7688/BioMedicalBertNer

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

https://github.com/kyegomez/GPT3

Language Models are Few-Shot Learners

https://github.com/kylitt/res

Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?

https://github.com/l4fl4m3/bmg

Bootstrapped Meta-Learning

https://github.com/laiviet/ed-fsl-extensive-matching

Extensively Matching for Few-shot Learning Event Detection

https://github.com/laiviet/maml

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

https://github.com/laiyongkui1997/FewJoint

FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.