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/Soikonomou/bert_new_new

Matching the Blanks: Distributional Similarity for Relation Learning

https://github.com/SoojungYang/supervised_pretraining_GN_WS

Big Transfer (BiT): General Visual Representation Learning

https://github.com/SoongE/siamese-one-shot-pytorch

https://github.com/StanfordVL/arxivbot

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks

https://github.com/SunghwanHong/Cost-Aggregation-transformers

Cost Aggregation Is All You Need for Few-Shot Segmentation

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

Language Models are Few-Shot Learners

https://github.com/TalSchuster/CrossLingualContextualEmb

Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing

https://github.com/Teddy00888/arn_mindspore

Few-shot Action Recognition with Permutation-invariant Attention

https://github.com/TejasAnvekar/Mahalanobis-k-NN

GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning

https://github.com/ThomasMiconi/LearningToLearnBOHP

Learning to learn with backpropagation of Hebbian plasticity

https://github.com/TianWuYuJiangHenShou/LabelSemantics

Label Semantics for Few Shot Named Entity Recognition

https://github.com/Tikquuss/meta_XLM

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

https://github.com/UIC-Liu-Lab/ContinualLM

Continual Training of Language Models for Few-Shot Learning

https://github.com/UTMIST/oneshot-data

The Omniglot challenge: a 3-year progress report

https://github.com/UTMIST/oneshot-rs

The Omniglot challenge: a 3-year progress report

https://github.com/VE-FORBRYDERNE/mtj-softtuner

The Power of Scale for Parameter-Efficient Prompt Tuning

https://github.com/VachanVY/gpt.jax

Language Models are Few-Shot Learners

https://github.com/ViswanathaReddyGajjala/FewShotWithoutForgetting

Dynamic Few-Shot Visual Learning without Forgetting

https://github.com/WangTianduo/Prototypical-Networks

Prototypical Networks for Few-shot Learning

https://github.com/WenbinLee/DN4

Matching Networks for One Shot Learning

https://github.com/YDU-uva/MetaKernel

Learning to Learn Kernels with Variational Random Features

https://github.com/YanFangCS/CyCTR-Pytorch

Few-Shot Segmentation via Cycle-Consistent Transformer

https://github.com/Yingjun-Du/MetaVRF

Learning to Learn Kernels with Variational Random Features

https://github.com/YoungHector/one-shot-mann

One-shot Learning with Memory-Augmented Neural Networks

https://github.com/Yuzhe-CHEN/NerfSNN

On First-Order Meta-Learning Algorithms

https://github.com/ZVK/Talking-Heads

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

https://github.com/ZVK/talking_heads

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

https://github.com/Zelgunn/MANN_tf_keras

One-shot Learning with Memory-Augmented Neural Networks

https://github.com/Zeng-WH/Prompt-Tuning

The Power of Scale for Parameter-Efficient Prompt Tuning

https://github.com/Zhiwei-Z/PrompLimitTest

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

https://github.com/Zhiwei-Z/SeqPromp

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

https://github.com/Zhiwei-Z/prompzzw

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

https://github.com/ZongrenZou/MHPINN

L-HYDRA: Multi-Head Physics-Informed Neural Networks

https://github.com/a-wozniakowski/scikit-physlearn

Boosting on the shoulders of giants in quantum device calibration

https://github.com/aadityasingh/icl-dynamics

Data Distributional Properties Drive Emergent In-Context Learning in Transformers

https://github.com/aadityasingh/icl-transience

Data Distributional Properties Drive Emergent In-Context Learning in Transformers

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