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/snowkylin/ntm

One-shot Learning with Memory-Augmented Neural Networks

https://github.com/social-ai-studio/pro-cap

Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations

https://github.com/soheeyang/unified-prompt-selection

Calibrate Before Use: Improving Few-Shot Performance of Language Models

https://github.com/sohiniroych/U-net_using_TF2

Few Shot Learning Framework to Reduce Inter-observer Variability in Medical Images

https://github.com/sohiniroych/Unet-using-TF2

Few Shot Learning Framework to Reduce Inter-observer Variability in Medical Images

https://github.com/sonnguyentruong129/siamese-oneshot

https://github.com/sorenbouma/keras-oneshot

https://github.com/sourachakra/densesubgraphsaliency

A dense subgraph based algorithm for compact salient image region detection

https://github.com/spiglerg/pyMeta

Meta-Learning with Implicit Gradients

https://github.com/squeezeailab/squeezellm

LLaMA: Open and Efficient Foundation Language Models

https://github.com/srgrace/contextual-compression

Extending Context Window of Large Language Models via Semantic Compression

https://github.com/stanfordbdhg/llama.cpp

LLaMA: Open and Efficient Foundation Language Models

https://github.com/stanfordnlp/dsp

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

https://github.com/stanislavfort/gaussian-prototypical-networks

Gaussian Prototypical Networks for Few-Shot Learning on Omniglot

https://github.com/stefanowoerner/medimeta-pytorch

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

https://github.com/stepjam/PyRep

Task-Embedded Control Networks for Few-Shot Imitation Learning

https://github.com/sungnyun/cd-fsl

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

https://github.com/sunyilgdx/prompts4keras

Entailment as Few-Shot Learner

https://github.com/susuxu-s-lab/hierarchical-earthquake-casualty-information-retrieval

Near-real-time Earthquake-induced Fatality Estimation using Crowdsourced Data and Large-Language Models

https://github.com/suvarna-kadam/Oct2018_Demo

Few-Shot Learning with Graph Neural Networks

https://github.com/swapnilagashe/Bi-directional_LSTM_for_NER

Few-shot Learning for Named Entity Recognition in Medical Text

https://github.com/tanhuajie/reason-rft

Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning

https://github.com/tatsu-lab/stanford_alpaca

LLaMA: Open and Efficient Foundation Language Models

https://github.com/teelinsan/camoscio

LLaMA: Open and Efficient Foundation Language Models

https://github.com/temibabs/I-RGCN

Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing

https://github.com/tensorfreitas/Siamese-Networks-for-One-Shot-Learning

https://github.com/tginart/sglang

SGLang: Efficient Execution of Structured Language Model Programs

https://github.com/theneuralbeing/maml

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

https://github.com/thunlp/clueanchor

Atlas: Few-shot Learning with Retrieval Augmented Language Models

https://github.com/thunlp/mode-connectivity-plm

CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP

https://github.com/tianheyu927/mil

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

https://github.com/timchen0618/pytorch-leo

Meta-Learning with Latent Embedding Optimization

https://github.com/timonziegenbein/inappropriateness-mitigation

LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback

https://github.com/tizzzzy/demonstration_selection_overview

In-Context Learning with Iterative Demonstration Selection

https://github.com/tjujianyu/rrl

A Closer Look at Few-shot Classification

https://github.com/tobiasvanderwerff/MetaHTR

Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

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