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/CGuangyan-BIT/PointGPT

공식 코드

PointGPT: Auto-regressively Generative Pre-training from Point Clouds

https://github.com/CLUEbenchmark/FewCLUE

공식 코드

FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark

https://github.com/Cerenaut/aha

공식 코드

Unsupervised One-shot Learning of Both Specific Instances and Generalised Classes with a Hippocampal Architecture

https://github.com/ChengtaiCao/Meta-GNN

공식 코드

Meta-GNN: On Few-shot Node Classification in Graph Meta-learning

https://github.com/ChunyuLiu188/SpectrumFM

공식 코드

SpectrumFM: A Foundation Model for Intelligent Spectrum Management

https://github.com/Clarifai/few-shot-ctm

공식 코드

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

https://github.com/Codelegant92/STC-MAML-PyTorch

공식 코드

An Investigation of Few-Shot Learning in Spoken Term Classification

https://github.com/Darthholi/similarity-models

공식 코드

Learning from similarity and information extraction from structured documents

https://github.com/DeLightCMU/ElaborativeRehearsal

공식 코드

Elaborative Rehearsal for Zero-shot Action Recognition

https://github.com/Dongqi-Fan/OnePoseTrans

공식 코드

One-Shot Learning for Pose-Guided Person Image Synthesis in the Wild

https://github.com/DreamH1gh/TACL2024

공식 코드

Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification

https://github.com/EavnJeong/Event_Modality_Application

공식 코드

Expanding Event Modality Applications through a Robust CLIP-Based Encoder

https://github.com/EdwinKim3069/XtarNet

공식 코드

XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning

https://github.com/Egg-Hu/BiDf-MKD

공식 코드

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning

https://github.com/ElementAI/baal

공식 코드

Synbols: Probing Learning Algorithms with Synthetic Datasets

https://github.com/ElementAI/synbols

공식 코드

Synbols: Probing Learning Algorithms with Synthetic Datasets

https://github.com/ElementAI/synbols-benchmarks

공식 코드

Synbols: Probing Learning Algorithms with Synthetic Datasets

https://github.com/EliSchwartz/DeltaEncoder

공식 코드

Delta-encoder: an effective sample synthesis method for few-shot object recognition

https://github.com/ExtensityAI/symbolicai

공식 코드

SymbolicAI: A framework for logic-based approaches combining generative models and solvers

https://github.com/FannierPeng/SgVA-CLIP

공식 코드

SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification

https://github.com/Fantabulous-J/FSMODQA

공식 코드

Few-Shot Multilingual Open-Domain QA from 5 Examples

https://github.com/FatemehAskari/MSENet

공식 코드

Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms

https://github.com/Fei-Long121/DeepBDC

공식 코드

Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification

https://github.com/Frankluox/Channel_Importance_FSL

공식 코드

Channel Importance Matters in Few-Shot Image Classification

https://github.com/Frankluox/FewShotCodeBase

공식 코드

Rectifying the Shortcut Learning of Background for Few-Shot Learning

https://github.com/Frozenmad/MetaDelta

공식 코드

MetaDelta: A Meta-Learning System for Few-shot Image Classification

https://github.com/GSK-AI/meta-learning-qsar

공식 코드

Meta-Learning Initializations for Low-Resource Drug Discovery

https://github.com/Gahyeonkim09/AAPL

공식 코드

AAPL: Adding Attributes to Prompt Learning for Vision-Language Models

https://github.com/GengDavid/CyCTR

공식 코드

Few-Shot Segmentation via Cycle-Consistent Transformer

https://github.com/GeorgeLuImmortal/RDL-Rationales-centric-Double-robustness-Learning

공식 코드

A Rationale-Centric Framework for Human-in-the-loop Machine Learning

https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training

공식 코드

Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks

https://github.com/Gordonjo/versa

공식 코드

Meta-Learning Probabilistic Inference For Prediction

https://github.com/Gorov/DiverseFewShot_Amazon

공식 코드

Diverse Few-Shot Text Classification with Multiple Metrics

https://github.com/GuodongQi/FSL-OM

공식 코드

Transductive Few-Shot Classification on the Oblique Manifold

https://github.com/HAIV-Lab/Knowe

공식 코드

Coarse-To-Fine Incremental Few-Shot Learning

https://github.com/HKUSTCV/FSS-1000

공식 코드

FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation

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