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/foolyc/Meta-SGD

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

https://github.com/foundation-model-stack/fms-fsdp

PaLM: Scaling Language Modeling with Pathways

https://github.com/freedomintelligence/huatuogpt

LLaMA: Open and Efficient Foundation Language Models

https://github.com/fsoft-ai4code/codecapybara

LLaMA: Open and Efficient Foundation Language Models

https://github.com/fujenchu/matchingNet

Matching Networks for One Shot Learning

https://github.com/fywalter/label-bias

Language Models are Few-Shot Learners

https://github.com/gabrielhuang/centroid-networks

Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time

https://github.com/gabrielhuang/reptile-pytorch

On First-Order Meta-Learning Algorithms

https://github.com/ganjinzero/rrhf

LLaMA: Open and Efficient Foundation Language Models

https://github.com/gaopengcuhk/tip-adapter

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

https://github.com/garyCC227/thesis

Adapted Deep Embeddings: A Synthesis of Methods for $k$-Shot Inductive Transfer Learning

https://github.com/gcucurull/maml_flax

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

https://github.com/gebob19/REPTILE-Metalearning

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

https://github.com/gebob19/cscd94-metalearning

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

https://github.com/gebob19/cscd94_metalearning

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

https://github.com/georgosgeorgos/few-shot-diffusion-models

Few-Shot Diffusion Models

https://github.com/ggerganov/llama.cpp

Language Models are Few-Shot Learners

https://github.com/ggml-org/llama.cpp

Language Models are Few-Shot Learners

https://github.com/giovanniguidi/logo-detection

A Deep One-Shot Network for Query-based Logo Retrieval

https://github.com/gitaar9/MLDAGAN

Data Augmentation Generative Adversarial Networks

https://github.com/gitabcworld/ConvArc

Attentive Recurrent Comparators

https://github.com/gjp1203/LIV360SV

IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments

https://github.com/glehet/ttm1

Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series

https://github.com/gmum/dl-mo-2021

Language Models are Few-Shot Learners

https://github.com/google-deepmind/emergent_in_context_learning

Data Distributional Properties Drive Emergent In-Context Learning in Transformers

https://github.com/google-deepmind/thunnini

The Power of Scale for Parameter-Efficient Prompt Tuning

https://github.com/google/paxml

PaLM: Scaling Language Modeling with Pathways

https://github.com/goolulusaurs/WorldModels

Gotta Learn Fast: A New Benchmark for Generalization in RL

https://github.com/gpt4life/alpagasus

GPT-4 Technical Report

https://github.com/grantslatton/llama.cpp

Language Models are Few-Shot Learners

https://github.com/greenbitai/low_bit_llama

LLaMA: Open and Efficient Foundation Language Models

https://github.com/grey-eye/talking-heads

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

https://github.com/griffbr/VOSVS

Mobile Robot Manipulation using Pure Object Detection

https://github.com/gudgud96/diff-wave-synth

Differentiable Wavetable Synthesis

https://github.com/guinmoon/llmfarm

LLaMA: Open and Efficient Foundation Language Models

https://github.com/haiyang-w/git

Language Models are Few-Shot Learners

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