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/clovaai/fewshot-font-generation

Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning

https://github.com/clrrrr/promp_plus

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

https://github.com/cnichkawde/MatchingNetwork

Matching Networks for One Shot Learning

https://github.com/cnielly/prototypical-networks-omniglot

Matching Networks for One Shot Learning

https://github.com/code-implementation1/Code5/tree/main/MAML

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

https://github.com/code-implementation1/Code5/tree/main/meta-baseline

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

https://github.com/code-implementation1/Code7/tree/main/relationnet

Learning to Compare: Relation Network for Few-Shot Learning

https://github.com/codedotal/gpt-code-clippy

Language Models are Few-Shot Learners

https://github.com/codelion/adaptive-classifier

Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning

https://github.com/compvis/latent-diffusion

LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

https://github.com/conceptofmind/PaLM-flax

PaLM: Scaling Language Modeling with Pathways

https://github.com/contextlab/abstract2paper

Language Models are Few-Shot Learners

https://github.com/corolla-johnson/mkultra

The Power of Scale for Parameter-Efficient Prompt Tuning

https://github.com/crashmoon/MAML-Pytorch-Multi-GPUs

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

https://github.com/crazydigger/Callibration-of-GPT

Language Models are Few-Shot Learners

https://github.com/cshhzhao/awesome-cross-domain-graph-learning

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

https://github.com/csyanbin/MAML-Pytorch-Multi-GPUs

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

https://github.com/csyanbin/TPN

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

https://github.com/cvl-umass/fsl_ssl

When Does Self-supervision Improve Few-shot Learning?

https://github.com/cypressd1999/FYP_2021

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

https://github.com/cyvius96/prototypical-network-pytorch

Prototypical Networks for Few-shot Learning

https://github.com/daiyk/daml_pytorch

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

https://github.com/damedollaforthree/nrml

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

https://github.com/damo-di-ml/neurips2023-one-fits-all

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

https://github.com/danielshalam/bpa

Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

https://github.com/dbaranchuk/memory-efficient-maml

Meta-Learning with Implicit Gradients

https://github.com/debonil/hate-speech-detection

Detecting Hate Speech with GPT-3

https://github.com/dfki-nlp/mtb-bert-em

Matching the Blanks: Distributional Similarity for Relation Learning

https://github.com/diffbot/knowledge-net

Matching the Blanks: Distributional Similarity for Relation Learning

https://github.com/divelab/vqa-text

Compact Bilinear Pooling

https://github.com/dkalpakchi/ReproducingSCAPytorch

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

https://github.com/dmcv-ecnu/MindSpore_ModelZoo/tree/main/EGNN%20Mindspore

Edge-labeling Graph Neural Network for Few-shot Learning

https://github.com/dmcv-ecnu/MindSpore_ModelZoo/tree/main/few-shot-meta-baseline_mindspore

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

https://github.com/dmis-lab/bern

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

https://github.com/doc-doc/NExT-OE

Flamingo: a Visual Language Model for Few-Shot Learning

https://github.com/dongheehand/MemoPainter-PyTorch

Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks

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