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/bhrqw/ari

공식 코드

Anti-Retroactive Interference for Lifelong Learning

https://github.com/bhrqw/sada

공식 코드

Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment

https://github.com/bids-xu-lab/clinical_entity_recognition_using_gpt_models

공식 코드

Improving Large Language Models for Clinical Named Entity Recognition via Prompt Engineering

https://github.com/bids-xu-lab/me-llama

공식 코드

Me LLaMA: Foundation Large Language Models for Medical Applications

https://github.com/bigdama/declarativeautoml

공식 코드

AutoML in Heavily Constrained Applications

https://github.com/bigdata-inha/zero-base-gfsl

공식 코드

Better Generalized Few-Shot Learning Even Without Base Data

https://github.com/bilaliman/rv_explainability

공식 코드

Generating Zero-shot Abstractive Explanations for Rumour Verification

https://github.com/billhhh/MCKD

공식 코드

Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data

https://github.com/bingykang/Fewshot_Detection

공식 코드

Few-shot Object Detection via Feature Reweighting

https://github.com/biomedia-repo/tseml

공식 코드

TSEML: A task-specific embedding-based method for few-shot classification of cancer molecular subtypes

https://github.com/biomedical-data-analysis-laboratory/adnet-for-ais-segmentation

공식 코드

Self-Supervised Few-Shot Learning for Ischemic Stroke Lesion Segmentation

https://github.com/biomistral/biomistral

공식 코드

BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains

https://github.com/bismex/MetaBIN

공식 코드

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

https://github.com/bjd39/lupi-ndp

공식 코드

Meta-learning using privileged information for dynamics

https://github.com/bkhmsi/alchemist

공식 코드

How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy

https://github.com/bl0/negative-margin.few-shot

공식 코드

Negative Margin Matters: Understanding Margin in Few-shot Classification

https://github.com/blpxspg/dbtm

공식 코드

Tracking Brand-Associated Polarity-Bearing Topics in User Reviews

https://github.com/bokun-wang/moml

공식 코드

Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning

https://github.com/borealisai/constant-memory-anp

공식 코드

Memory Efficient Neural Processes via Constant Memory Attention Block

https://github.com/borealisai/latent-bottlenecked-anp

공식 코드

Latent Bottlenecked Attentive Neural Processes

https://github.com/boschresearch/MetaBO

공식 코드

Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization

https://github.com/boschresearch/meta-adversarial-training

공식 코드

Meta Adversarial Training against Universal Patches

https://github.com/boschresearch/meta-learning-likelihood-free-bayesian-optimization

공식 코드

MALIBO: Meta-learning for Likelihood-free Bayesian Optimization

https://github.com/boschresearch/meta-rs

공식 코드

Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks

https://github.com/boschresearch/metanas

공식 코드

Meta-Learning of Neural Architectures for Few-Shot Learning

https://github.com/boschresearch/what-matters-for-meta-learning

공식 코드

What Matters For Meta-Learning Vision Regression Tasks?

https://github.com/bosonphoton/abstractedgaussianprototypes

공식 코드

Abstracted Gaussian Prototypes for One-Shot Concept Learning

https://github.com/brain-cog-lab/n-omniglot

공식 코드

N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning

https://github.com/brain-research/guided-evolutionary-strategies

공식 코드

Guided evolutionary strategies: Augmenting random search with surrogate gradients

https://github.com/brando90/Does-MAML-Only-Work-via-Feature-Re-use-A-Data-Set-Centric-Perspective

공식 코드

Does MAML Only Work via Feature Re-use? A Data Centric Perspective

https://github.com/brandon3964/multimodal-task-vector

공식 코드

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning

https://github.com/breakaway7/p3dc-shot

공식 코드

P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification

https://github.com/breakend/selfdestructingmodels

공식 코드

Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models

https://github.com/brendenlake/omniglot

공식 코드

The Omniglot challenge: a 3-year progress report

https://github.com/brettfyt/ss_via_llms

공식 코드

Sentence Simplification via Large Language Models

https://github.com/brinkl/graphhetnet

공식 코드

Few-shot human motion prediction for heterogeneous sensors

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