Papers with Code 아카이브

Meta-Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 3
평가표: 4
보존된 평가 기록: 13

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

<span style="color:grey; opacity: 0.6">( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )</span>

코드

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

https://github.com/kl4805/shoppingmmlu

공식 코드

Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models

https://github.com/knoriy/CLARA

공식 코드

CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition

https://github.com/knowledge-ukraine/ontochatgpt

공식 코드

OntoChatGPT Information System: Ontology-Driven Structured Prompts for ChatGPT Meta-Learning

https://github.com/knowledgetechnologyuhh/drill

공식 코드

DRILL: Dynamic Representations for Imbalanced Lifelong Learning

https://github.com/koava36/certrob-fewshot

공식 코드

Smoothed Embeddings for Certified Few-Shot Learning

https://github.com/kojima-takeshi188/zero_shot_cot

공식 코드

Large Language Models are Zero-Shot Reasoners

https://github.com/komeijiforce/cotam

공식 코드

Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation

https://github.com/koncle/mvdg

공식 코드

MVDG: A Unified Multi-view Framework for Domain Generalization

https://github.com/koushiksrivats/face_attribute_attack

공식 코드

Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces

https://github.com/kpeng9510/ebil-hads

공식 코드

Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler

https://github.com/kpeng9510/hyprometa

공식 코드

Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization

https://github.com/krasheninnikov/internalization

공식 코드

Implicit meta-learning may lead language models to trust more reliable sources

https://github.com/kristian-georgiev/sgmrl

공식 코드

On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning

https://github.com/krunolp/mars

공식 코드

MARS: Meta-Learning as Score Matching in the Function Space

https://github.com/ktr-hubrt/MPN

공식 코드

Learning Normal Dynamics in Videos with Meta Prototype Network

https://github.com/kuennethgroup/organic_battery_predictor

공식 코드

AI-Driven Discovery of High Performance Polymer Electrodes for Next-Generation Batteries

https://github.com/kuku-sichuan/ComparisonDetector

공식 코드

Comparison-Based Convolutional Neural Networks for Cervical Cell/Clumps Detection in the Limited Data Scenario

https://github.com/kuroo/famp

공식 코드

Reusable Options through Gradient-based Meta Learning

https://github.com/kyk120/pointfix

공식 코드

PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation

https://github.com/kyxscut/CG-GAN

공식 코드

Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator

https://github.com/laiyingxin2/gm-df

공식 코드

GM-DF: Generalized Multi-Scenario Deepfake Detection

https://github.com/lamsoma/auto_nli

공식 코드

Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples

https://github.com/laquabe/OneNet

공식 코드

OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting

https://github.com/lars-research/pacia

공식 코드

PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction

https://github.com/launchnlp/politics

공식 코드

POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection

https://github.com/lavine-lmu/m4adapter

공식 코드

$m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter

https://github.com/lavine-lmu/rmlnmt

공식 코드

Improving Both Domain Robustness and Domain Adaptability in Machine Translation

https://github.com/layer6ai-labs/DRESS

공식 코드

DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks

https://github.com/lccc0528/stable

공식 코드

StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation

https://github.com/ldery/tartan

공식 코드

Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative

https://github.com/leaplabthu/l2w-den

공식 코드

Learning to Weight Samples for Dynamic Early-exiting Networks

https://github.com/learnables/learn2learn

공식 코드

Generalized Inner Loop Meta-Learning

https://github.com/learningtitans/isbi2017-part1

공식 코드

RECOD Titans at ISIC Challenge 2017

https://github.com/learningtitans/isbi2017-part3

공식 코드

RECOD Titans at ISIC Challenge 2017

https://github.com/leenamx/ge-fsod

공식 코드

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing

https://github.com/leezythu/MetaBLINK

공식 코드

Effective Few-Shot Named Entity Linking by Meta-Learning

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