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/hamishivi/easylm

LLaMA: Open and Efficient Foundation Language Models

https://github.com/hannight/amulap

Making Pre-trained Language Models Better Few-shot Learners

https://github.com/happen2me/cross-gnn

Flamingo: a Visual Language Model for Few-Shot Learning

https://github.com/hazyresearch/ama_prompting

Language Models are Few-Shot Learners

https://github.com/hazyresearch/safari

Hungry Hungry Hippos: Towards Language Modeling with State Space Models

https://github.com/hellokevin07/elastictrainer

The Power of Scale for Parameter-Efficient Prompt Tuning

https://github.com/henry-prior/multimodal-rl

Grounded Language Learning Fast and Slow

https://github.com/hfahrudin/reptile_implement_tf2

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

https://github.com/hhl60492/deep-kernel-transfer

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

https://github.com/hieudepchai/BERT_IE

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

https://github.com/hilberthit/gpt-3

Language Models are Few-Shot Learners

https://github.com/hmishra2250/NTM-One-Shot-TF

One-shot Learning with Memory-Augmented Neural Networks

https://github.com/hojjat-mokhtarabadi/promptsource

Language Models are Few-Shot Learners

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

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

https://github.com/hrdwsong/ProtoNet-Paddle

Matching Networks for One Shot Learning

https://github.com/huang-research-group/globalfsl2019

Few-Shot Learning with Global Class Representations

https://github.com/huggingface/alignment-handbook

Zephyr: Direct Distillation of LM Alignment

https://github.com/huggingface/transformers

LLaMA: Open and Efficient Foundation Language Models

https://github.com/hw666666666666/BigTransfer

Big Transfer (BiT): General Visual Representation Learning

https://github.com/hy-zpg/DAGAN

Data Augmentation Generative Adversarial Networks

https://github.com/hy-zpg/FIGR

FIGR: Few-shot Image Generation with Reptile

https://github.com/iandrover/maml_noisy_contrasive_learner

MAML is a Noisy Contrastive Learner in Classification

https://github.com/ibm-self-serve-assets/metagen-blended-rag

MetaGen Blended RAG: Higher Accuracy for Domain-Specific Q&A Without Fine-Tuning

https://github.com/icalk-nlp/educhat

LLaMA: Open and Efficient Foundation Language Models

https://github.com/iclavera/meta-mb

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

https://github.com/icoz69/CaNet

CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning

https://github.com/icoz69/DeepEMD

Meta-learning with differentiable closed-form solvers

https://github.com/ido90/roml-maml

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

https://github.com/idsia/neuraldiffeq-fwp

A Modern Self-Referential Weight Matrix That Learns to Modify Itself

https://github.com/infinitemugen/MAML-Pytorch

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

https://github.com/insait-institute/lm-evaluation-harness-bg

Language Models are Few-Shot Learners

https://github.com/jacobandreas/geca

Human few-shot learning of compositional instructions

https://github.com/jaekyeom/mabas

Dynamic Few-Shot Visual Learning without Forgetting

https://github.com/jiachangliu/kategpt3

What Makes Good In-Context Examples for GPT-$3$?

https://github.com/jiakangyuan/helixformer

Learning to Compare: Relation Network for Few-Shot Learning

https://github.com/jiean001/models_m/tree/main/LEO

Meta-Learning with Latent Embedding Optimization

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