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/coteries/cedille-ai

공식 코드

Cedille: A large autoregressive French language model

https://github.com/cpphoo/STARTUP

공식 코드

Self-training for Few-shot Transfer Across Extreme Task Differences

https://github.com/cps11/darl

공식 코드

Reinforcement Learning for Few-Shot Text Generation Adaptation

https://github.com/crisostomi/metric-few-shot-graph

공식 코드

Metric Based Few-Shot Graph Classification

https://github.com/cser-tang-hao/bsfa-fsfg

공식 코드

Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment

https://github.com/cshhzhao/gcope

공식 코드

All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining

https://github.com/csyanbin/TPN-pytorch

공식 코드

Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning

https://github.com/ctom2/latent-space-transform

공식 코드

Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

https://github.com/cutz-j/FDFtNet

공식 코드

FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network

https://github.com/cv516buaa/sd-aanet

공식 코드

A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation

https://github.com/cvjena/semantic-embeddings

공식 코드

Hierarchy-based Image Embeddings for Semantic Image Retrieval

https://github.com/cvl-hub/gprn

공식 코드

SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation

https://github.com/cvlab-stonybrook/fsl-rsvae

공식 코드

Generating Representative Samples for Few-Shot Classification

https://github.com/cvxgrp/joint-lrsm

공식 코드

Joint Graph Learning and Model Fitting in Laplacian Regularized Stratified Models

https://github.com/cyvius96/few-shot-meta-baseline

공식 코드

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

https://github.com/czifan/raml

공식 코드

Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation

https://github.com/czq142857/BAE-NET

공식 코드

BAE-NET: Branched Autoencoder for Shape Co-Segmentation

https://github.com/czx-li/DP2O

공식 코드

Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning

https://github.com/czyssrs/Few-Shot-NLG

공식 코드

Few-Shot NLG with Pre-Trained Language Model

https://github.com/dahyun-kang/ifsl

공식 코드

Integrative Few-Shot Learning for Classification and Segmentation

https://github.com/dali92002/htrbymatching

공식 코드

Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text Recognition

https://github.com/dammsi/AnomalyDINO

공식 코드

AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2

https://github.com/damo-di-ml/one_fits_all

공식 코드

One Fits All:Power General Time Series Analysis by Pretrained LM

https://github.com/damo-nlp-sg/llm-sentiment

공식 코드

Sentiment Analysis in the Era of Large Language Models: A Reality Check

https://github.com/danhntd/FS-CDIS

공식 코드

The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation

https://github.com/dannyallover/overthinking_the_truth

공식 코드

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

https://github.com/dasepli/codeie

공식 코드

CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors

https://github.com/daviswer/fewshotlocal

공식 코드

Few-Shot Learning with Localization in Realistic Settings

https://github.com/davor10105/laat

공식 코드

Large Language Models as Attribution Regularizers for Efficient Model Training

https://github.com/dchiji-ntt/meta-ticket

공식 코드

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks

https://github.com/dddavid4real/focus

공식 코드

FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification

https://github.com/debabratapal7/dafosnet

공식 코드

Domain Adaptive Few-Shot Open-Set Learning

https://github.com/debarshigit/promptmargin

공식 코드

Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution Shifts

https://github.com/deep-symbolic-mathematics/Multimodal-Math-Pretraining

공식 코드

SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training

https://github.com/deep-symbolic-mathematics/Multimodal-Symbolic-Regression

공식 코드

SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training

https://github.com/deepmind/emergent_in_context_learning

공식 코드

Data Distributional Properties Drive Emergent In-Context Learning in Transformers

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