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/yangyangyang127/seg-nn

공식 코드

No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation

https://github.com/yangyongjin/melo

공식 코드

Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation

https://github.com/yaniker/one-shot-skill-assessment-in-high-stakes-domains-with-limited-data-via-meta-learning

공식 코드

One-shot skill assessment in high-stakes domains with limited data via meta learning

https://github.com/yaoyao-liu/E3BM

공식 코드

An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning

https://github.com/yaoyao-liu/meta-transfer-learning

공식 코드

Meta-Transfer Learning for Few-Shot Learning

https://github.com/yassouali/SCL

공식 코드

Spatial Contrastive Learning for Few-Shot Classification

https://github.com/yazhouzhu19/rpt

공식 코드

Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer

https://github.com/ybendou/easy

공식 코드

EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients

https://github.com/ybendou/fs-generalization

공식 코드

A Statistical Model for Predicting Generalization in Few-Shot Classification

https://github.com/ybendou/fs-text2stats

공식 코드

Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning

https://github.com/ybzh/point-dae

공식 코드

Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning

https://github.com/ycfate/id-like

공식 코드

ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection

https://github.com/ycm094/mg-fte-main

공식 코드

Mutually Guided Few-shot Learning for Relational Triple Extraction

https://github.com/yczhou001/ClarET

공식 코드

ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification

https://github.com/ydu-uva/hiermemory

공식 코드

Hierarchical Variational Memory for Few-shot Learning Across Domains

https://github.com/ydu-uva/protodiff

공식 코드

ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion

https://github.com/yfguo91/neuroclip

공식 코드

NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNN

https://github.com/yhu01/PT-MAP

공식 코드

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

https://github.com/yhu01/bms

공식 코드

Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning

https://github.com/yilun-wu/MetaL-Benchmark

공식 코드

ALPaCA vs. GP-based Prior Learning: A Comparison between two Bayesian Meta-Learning Algorithms

https://github.com/yilunzhao/robut

공식 코드

RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations

https://github.com/yinboc/few-shot-meta-baseline

공식 코드

Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning

https://github.com/yingutk/NL-MAT

공식 코드

Non-Local Representation based Mutual Affine-Transfer Network for Photorealistic Stylization

https://github.com/yiren-jian/labelhalluc

공식 코드

Label Hallucination for Few-Shot Classification

https://github.com/yitewang/metantk-nas

공식 코드

Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning

https://github.com/yizhouzhao/tangram

공식 코드

Learning from the Tangram to Solve Mini Visual Tasks

https://github.com/yli1/CGPS

공식 코드

Compositional Generalization for Primitive Substitutions

https://github.com/yongchao97/diffusion_inversion

공식 코드

Training on Thin Air: Improve Image Classification with Generated Data

https://github.com/youngjae-cho/app

공식 코드

Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior

https://github.com/youthhoo/afa_for_few_shot_learning

공식 코드

Adversarial Feature Augmentation for Cross-domain Few-shot Classification

https://github.com/yue-zhongqi/ifsl

공식 코드

Interventional Few-Shot Learning

https://github.com/yue-zhongqi/tif

공식 코드

Few-shot Learner Parameterization by Diffusion Time-steps

https://github.com/yuhangzang/upt

공식 코드

Unified Vision and Language Prompt Learning

https://github.com/yuhao318/btm

공식 코드

Reviving Undersampling for Long-Tailed Learning

https://github.com/yukang-lin/rger

공식 코드

Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning

https://github.com/yul091/graphlogad

공식 코드

GLAD: Content-aware Dynamic Graphs For Log Anomaly Detection

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