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/zihangJiang/Adaptive-Attention

공식 코드

Few-shot Classification via Adaptive Attention

https://github.com/zihangm/Differentiable-LP-Layer

공식 코드

Physarum Powered Differentiable Linear Programming Layers and Applications

https://github.com/zihangm/Physarum-Differentiable-LP-Layer

공식 코드

Physarum Powered Differentiable Linear Programming Layers and Applications

https://github.com/zihangm/neural-tmd-layer

공식 코드

Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators

https://github.com/zihaohe123/norm-violation-detection-prompt-based

공식 코드

CPL-NoViD: Context-Aware Prompt-based Learning for Norm Violation Detection in Online Communities

https://github.com/ziqihuangg/reversion

공식 코드

ReVersion: Diffusion-Based Relation Inversion from Images

https://github.com/zjunlp/DART

공식 코드

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

https://github.com/zjunlp/DeepKE/tree/main/example/ner/few-shot

공식 코드

LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting

https://github.com/zjunlp/PromptKG/tree/main/research/RetrievalRE

공식 코드

Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning

https://github.com/zoilsen/flor

공식 코드

Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning

https://github.com/zouxinyi0625/cdnet

공식 코드

Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition

https://github.com/zpx16900/DGGN

공식 코드

Edge-Labeling based Directed Gated Graph Network for Few-shot Learning

https://github.com/zrrskywalker/cafo

공식 코드

Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners

https://github.com/zrrskywalker/pointclip

공식 코드

PointCLIP: Point Cloud Understanding by CLIP

https://github.com/zshanggu/cdmm

공식 코드

Cross-domain Multi-modal Few-shot Object Detection via Rich Text

https://github.com/zuwenqiang/ept

공식 코드

Embedded Prompt Tuning: Towards Enhanced Calibration of Pretrained Models for Medical Images

https://github.com/zwzheng98/qclnet

공식 코드

Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation

https://github.com/zyn-1101/dandr

공식 코드

Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective

https://github.com/zzqzzq/bml

공식 코드

Binocular Mutual Learning for Improving Few-shot Classification

https://gitlab.anu.edu.au/u6554606/eaen

공식 코드

Episode Adaptive Embedding Networks for Few-shot Learning

https://gitlab.com/bruno_viti/gpe_4_cardiac_fss

공식 코드

Gaussian Process Emulators for Few-Shot Segmentation in Cardiac MRI

https://gitlab.com/farid-fari/fewshot-learning

공식 코드

Few-shot learning through contextual data augmentation

https://gitlab.kitware.com/darpa_learn/learn

공식 코드

LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning

https://huggingface.co/ibm/materials.smi-ted

공식 코드

A Large Encoder-Decoder Family of Foundation Models For Chemical Language

https://dagshub.com/Dean/BioBERT-DAGsHub

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

https://dagshub.com/arjun2000ashok/FSL-SSL

When Does Self-supervision Improve Few-shot Learning?

https://github.com/2006pmach/awesome-few-shot-object-detection

Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment

https://github.com/2023-MindSpore-1/ms-code-106

An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning

https://github.com/2023-MindSpore-1/ms-code-141

Unsupervisedly Prompting AlphaFold2 for Few-Shot Learning of Accurate Folding Landscape and Protein Structure Prediction

https://github.com/2023-MindSpore-1/ms-code-210/tree/main/CMT

CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search

https://github.com/2023-MindSpore-1/ms-code-216/tree/main/relationnet

RelationNet2: Deep Comparison Columns for Few-Shot Learning

https://github.com/2023-MindSpore-1/ms-code-217/tree/main/unisiam

Self-Supervision Can Be a Good Few-Shot Learner

https://github.com/2023-MindSpore-1/ms-code-6

An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning

https://github.com/2023-MindSpore-1/ms-code-6/tree/main/CMT

CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search

https://github.com/2023-MindSpore-4/Code-5/tree/main/MAML

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

https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama

LLaMA: Open and Efficient Foundation Language Models

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