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/Learning-and-Intelligent-Systems/Analytical-Learning-Theory

공식 코드

Generalization in Machine Learning via Analytical Learning Theory

https://github.com/Learning-and-Intelligent-Systems/DualCutout

공식 코드

Generalization in Machine Learning via Analytical Learning Theory

https://github.com/LiheYoung/MiningFSS

공식 코드

Mining Latent Classes for Few-shot Segmentation

https://github.com/Lirain21/UniMatch

공식 코드

UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery

https://github.com/LouieYang/MCL

공식 코드

Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification

https://github.com/MAN-author/MAN

공식 코드

Multi-Pretext Attention Network for Few-shot Learning with Self-supervision

https://github.com/MCG-NJU/AWT

공식 코드

AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

https://github.com/ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers

공식 코드

Revisiting Discriminative vs. Generative Classifiers: Theory and Implications

https://github.com/MSiam/AdaptiveMaskedProxies

공식 코드

Adaptive Masked Proxies for Few-Shot Segmentation

https://github.com/MaxZanella/transduction-for-vlms

공식 코드

Boosting Vision-Language Models with Transduction

https://github.com/McGill-NLP/latent-translation

공식 코드

Modelling Latent Translations for Cross-Lingual Transfer

https://github.com/MegviiDetection/FSCE

공식 코드

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

https://github.com/Michael-Tanzer/BERT-mem-lowres

공식 코드

Memorisation versus Generalisation in Pre-trained Language Models

https://github.com/Mukaffi28/Bengali-Political-Sentiment-Analysis

공식 코드

Motamot: A Dataset for Revealing the Supremacy of Large Language Models over Transformer Models in Bengali Political Sentiment Analysis

https://github.com/MyChocer/KGTN

공식 코드

Knowledge Graph Transfer Network for Few-Shot Recognition

https://github.com/NVIDIA/audio-flamingo

공식 코드

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

https://github.com/NamyeongK/USA_UFGSM

공식 코드

Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning

https://github.com/NesterukSergey/segmentation_image_augmentation

공식 코드

Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-Case

https://github.com/Neutralzz/RefQA

공식 코드

Harvesting and Refining Question-Answer Pairs for Unsupervised QA

https://github.com/Nithin-Holla/MetaWSD

공식 코드

Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation

https://github.com/OasisYang/SSG

공식 코드

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification

https://github.com/OctThe16th/FIGR

공식 코드

FIGR: Few-shot Image Generation with Reptile

https://github.com/Ouasfi/FS-SDF

공식 코드

Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space

https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-3.0

공식 코드

ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation

https://github.com/Pang-Yatian/Point-MAE

공식 코드

Masked Autoencoders for Point Cloud Self-supervised Learning

https://github.com/PolyAI-LDN/task-specific-datasets

공식 코드

Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations

https://github.com/PongNJ/V-RoAst

공식 코드

V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?

https://github.com/Prasath2001/Party-Symbol-Classifier

공식 코드

An AI-Powered VVPAT Counter for Elections in India

https://github.com/Pulkit-Khandelwal/medical-mldg-seg

공식 코드

Domain Generalizer: A Few-shot Meta Learning Framework for Domain Generalization in Medical Imaging

https://github.com/RS2002/CrossFi

공식 코드

CrossFi: A Cross Domain Wi-Fi Sensing Framework Based on Siamese Network

https://github.com/RS2002/KNN-MMD

공식 코드

KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment

https://github.com/RamnathKumar181/Task-Diversity-meta-learning

공식 코드

The Effect of Diversity in Meta-Learning

https://github.com/Reagan1311/ASGNet

공식 코드

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

https://github.com/Reza-esfandiarpoor/pseudo-shots

공식 코드

Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks

https://github.com/RongKaiWeskerMA/INSTA

공식 코드

Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning

https://github.com/RuohanW/Tasml

공식 코드

Structured Prediction for Conditional Meta-Learning

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