Papers with Code 아카이브

Few-Shot Image Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 3
평가표: 89
보존된 평가 기록: 913

Few-Shot Image Classification is a computer vision task that involves training machine learning models to classify images into predefined categories using only a few labeled examples of each category (typically < 6 examples). The goal is to enable models to recognize and classify new images with minimal supervision and limited data, without having to train on large datasets. (typically < 6 examples)

<span style="color:grey; opacity: 0.6">( Image credit: Learning Embedding Adaptation for Few-Shot Learning )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

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

공식 코드

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

https://github.com/Sha-Lab/FEAT

공식 코드

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

https://github.com/Tsingularity/FRN

공식 코드

Few-Shot Classification with Feature Map Reconstruction Networks

https://github.com/VICO-UoE/URL

공식 코드

Universal Representation Learning from Multiple Domains for Few-shot Classification

https://github.com/Vanint/TADE-AgnosticLT

공식 코드

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

https://github.com/WangYueFt/rfs

공식 코드

Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?

https://github.com/Westlake-AI/SemiReward

공식 코드

SemiReward: A General Reward Model for Semi-supervised Learning

https://github.com/WonderSeven/ULDA

공식 코드

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

https://github.com/XuZhengzhuo/Prior-LT

공식 코드

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

https://github.com/Yikai-Wang/ICI-FSL

공식 코드

Instance Credibility Inference for Few-Shot Learning

https://github.com/YuMJie/ConCutMix

공식 코드

Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation

https://github.com/YutingLi0606/SURE

공식 코드

SURE: SUrvey REcipes for building reliable and robust deep networks

https://github.com/YyzHarry/imbalanced-semi-self

공식 코드

Rethinking the Value of Labels for Improving Class-Imbalanced Learning

https://github.com/abdullahjamal/Longtail_DA

공식 코드

Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

https://github.com/abdulvahapmutlu/vit-protonet

공식 코드

ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation

https://github.com/alcunha/bagoftricks4cameratraps

공식 코드

Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images

https://github.com/alinlab/M2m

공식 코드

M2m: Imbalanced Classification via Major-to-minor Translation

https://github.com/alinlab/psco

공식 코드

Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

https://github.com/allanyangzhou/generative-invariance-transfer

공식 코드

Do Deep Networks Transfer Invariances Across Classes?

https://github.com/amazon-science/few-shot-baseline

공식 코드

A Baseline for Few-Shot Image Classification

https://github.com/amberyzheng/LTO

공식 코드

Learning to Obstruct Few-Shot Image Classification over Restricted Classes

https://github.com/amirziai/rafic

공식 코드

RAFIC: Retrieval-Augmented Few-shot Image Classification

https://github.com/amzn/xfer

공식 코드

Empirical Bayes Transductive Meta-Learning with Synthetic Gradients

https://github.com/andrewbo29/mtm-meta-learning-sa

공식 코드

Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning

https://github.com/anish-lu-yihe/pySVRT

공식 코드

Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Test

https://github.com/anujinho/trident

공식 코드

Transductive Decoupled Variational Inference for Few-Shot Classification

https://github.com/aravindr93/imaml_dev

공식 코드

Meta-Learning with Implicit Gradients

https://github.com/arjish/PreTrainedFullLibrary_FewShot

공식 코드

Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier

https://github.com/automl/transformerscandobayesianinference

공식 코드

Transformers Can Do Bayesian Inference

https://github.com/bazinga699/ncl

공식 코드

Nested Collaborative Learning for Long-Tailed Visual Recognition

https://github.com/bbbdylan/unisiam

공식 코드

Self-Supervision Can Be a Good Few-Shot Learner

https://github.com/bl0/negative-margin.few-shot

공식 코드

Negative Margin Matters: Understanding Margin in Few-shot Classification

https://github.com/bluecdm/Long-tailed-recognition

공식 코드

Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels

https://github.com/boyiliee/sitta

공식 코드

SITTA: Single Image Texture Translation for Data Augmentation

https://github.com/boyuh/aucseg

공식 코드

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

https://github.com/brandontrabucco/da-fusion

공식 코드

Effective Data Augmentation With Diffusion Models

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