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/bytedance/GR-MG

공식 코드

GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy

https://github.com/c-juhwan/unigen

공식 코드

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation

https://github.com/c4dm/dcase-few-shot-bioacoustic

공식 코드

Few-shot bioacoustic event detection at the DCASE 2023 challenge

https://github.com/caesarea38/doclangid

공식 코드

DocLangID: Improving Few-Shot Training to Identify the Language of Historical Documents

https://github.com/callanwu/star

공식 코드

STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models

https://github.com/callmesanfornow/fsl-audio-abuse

공식 코드

Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning

https://github.com/calvinyeungck/automated_assignment_grading

공식 코드

A Zero-Shot LLM Framework for Automatic Assignment Grading in Higher Education

https://github.com/cambridge-mlg/cnaps

공식 코드

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

https://github.com/cambridge-mlg/fit

공식 코드

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

https://github.com/cambridgeltl/prompt4bli

공식 코드

On Bilingual Lexicon Induction with Large Language Models

https://github.com/cambridgeltl/sail-bli

공식 코드

Self-Augmented In-Context Learning for Unsupervised Word Translation

https://github.com/came-thu/flamepinn-1d

공식 코드

FlamePINN-1D: Physics-informed neural networks to solve forward and inverse problems of 1D laminar flames

https://github.com/camma-public/peskavlp

공식 코드

Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures

https://github.com/camma-public/surgvlp

공식 코드

Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures

https://github.com/canyuchen/promptda

공식 코드

PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners

https://github.com/caoji2001/hoser

공식 코드

Holistic Semantic Representation for Navigational Trajectory Generation

https://github.com/cbfinn/maml

공식 코드

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

https://github.com/cbfinn/maml_rl

공식 코드

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

https://github.com/cc13qq/cad

공식 코드

Continual Adversarial Defense

https://github.com/cea-list/metamtreg

공식 코드

Improving Few-Shot Learning through Multi-task Representation Learning Theory

https://github.com/centre-for-humanities-computing/llm-tweet-classification

공식 코드

Chatbots Are Not Reliable Text Annotators

https://github.com/cerenaut/cfsl

공식 코드

Expanding continual few-shot learning benchmarks to include recognition of specific instances

https://github.com/cfifty/ignite

공식 코드

Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction

https://github.com/cgye96/a_closer_look_at_3dfsl

공식 코드

A Closer Look at Few-Shot 3D Point Cloud Classification

https://github.com/changshuowang/GPSFormer

공식 코드

GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding

https://github.com/charlesjin/synthetic_data

공식 코드

Towards Context-Agnostic Learning Using Synthetic Data

https://github.com/charliezhaoyinpeng/PDFM

공식 코드

A Primal-Dual Subgradient Approachfor Fair Meta Learning

https://github.com/chauhanjatin10/GraphsFewShot

공식 코드

Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures

https://github.com/cheggan/metaaudio-a-few-shot-audio-classification-benchmark

공식 코드

MetaAudio: A Few-Shot Audio Classification Benchmark

https://github.com/cheggan/mt-slvr

공식 코드

MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations

https://github.com/cheneydon/hrkd

공식 코드

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression

https://github.com/cheng-01037/Self-supervised-Fewshot-Medical-Image-Segmentation

공식 코드

Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation

https://github.com/chengcv/dfrfs

공식 코드

Disentangled Feature Representation for Few-shot Image Classification

https://github.com/chenguolin/nutime

공식 코드

NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining

https://github.com/chenhaoxing/ASL

공식 코드

Shaping Visual Representations with Attributes for Few-Shot Recognition

https://github.com/chenhaoxing/cpr

공식 코드

Conditional Prototype Rectification Prompt Learning

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