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/yumeng5/fewgen

공식 코드

Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning

https://github.com/yumeng5/supergen

공식 코드

Generating Training Data with Language Models: Towards Zero-Shot Language Understanding

https://github.com/yushi-hu/ic-dst

공식 코드

In-Context Learning for Few-Shot Dialogue State Tracking

https://github.com/yuvenduan/plasticrnns

공식 코드

Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs

https://github.com/zaplm/dc-sam

공식 코드

DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency

https://github.com/zbf1991/SCL

공식 코드

Self-Guided and Cross-Guided Learning for Few-Shot Segmentation

https://github.com/zcrwind/tgg-pytorch

공식 코드

TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning

https://github.com/zdsy/proto-MAML

공식 코드

Episodic fine-tuning prototypical networks for optimization-based few-shot learning: Application to audio classification

https://github.com/zgjiangtoby/FND_fewshot

공식 코드

Cross-Modal Augmentation for Few-Shot Multimodal Fake News Detection

https://github.com/zhang-lingyun/ConceptReplacer

공식 코드

Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization

https://github.com/zhangbq-research/Prototype_Completion_for_FSL

공식 코드

Prototype Completion with Primitive Knowledge for Few-Shot Learning

https://github.com/zhangbq-research/metanode

공식 코드

MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning

https://github.com/zhangce01/dualadapter

공식 코드

Enhancing Vision-Language Few-Shot Adaptation with Negative Learning

https://github.com/zhangce01/simnl

공식 코드

Enhancing Vision-Language Few-Shot Adaptation with Negative Learning

https://github.com/zhangdoudou123/semfew

공식 코드

Simple Semantic-Aided Few-Shot Learning

https://github.com/zhangtao2022/dsfn

공식 코드

Kernel Relative-prototype Spectral Filtering for Few-shot Learning

https://github.com/zhangxueting/DCN

공식 코드

RelationNet2: Deep Comparison Columns for Few-Shot Learning

https://github.com/zhangyilang/metamirrordescent

공식 코드

Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent

https://github.com/zhangzilongc/sofs

공식 코드

Small Object Few-shot Segmentation for Vision-based Industrial Inspection

https://github.com/zhaohengyuan1/sct

공식 코드

SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels

https://github.com/zhengli97/dm-kd

공식 코드

Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?

https://github.com/zhengxiangshi/dept

공식 코드

DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

https://github.com/zhengxiangshi/powerfulpromptft

공식 코드

Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis

https://github.com/zheyangh/ocgnet

공식 코드

Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention

https://github.com/zhiheLu/CWT-for-FSS

공식 코드

Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer

https://github.com/zhimin-c/multiview-mae

공식 코드

Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder

https://github.com/zhipeng-wei/EmojiAttack

공식 코드

Emoji Attack: A Method for Misleading Judge LLMs in Safety Risk Detection

https://github.com/zhongwanjun/proqa

공식 코드

ProQA: Structural Prompt-based Pre-training for Unified Question Answering

https://github.com/zhouj8553/flipda

공식 코드

FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning

https://github.com/zhoulong0/unem-transductive

공식 코드

UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning

https://github.com/zhuang-li/few-shot-semantic-parsing

공식 코드

Few-Shot Semantic Parsing for New Predicates

https://github.com/zhuang-li/vae-dprior

공식 코드

Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation

https://github.com/zhuhsingyuu/ssp

공식 코드

Selective Vision-Language Subspace Projection for Few-shot CLIP

https://github.com/zhuyun97/graphclip

공식 코드

GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs

https://github.com/zhw12/BERTRL

공식 코드

Inductive Relation Prediction by BERT

https://github.com/zifengding/fitcarl

공식 코드

Improving Few-Shot Inductive Learning on Temporal Knowledge Graphs using Confidence-Augmented Reinforcement Learning

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