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/facebookresearch/maws

공식 코드

The effectiveness of MAE pre-pretraining for billion-scale pretraining

https://github.com/fistyee/LTRL

공식 코드

LTRL: Boosting Long-tail Recognition via Reflective Learning

https://github.com/fistyee/mdcs

공식 코드

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

https://github.com/flamiezhu/bcl

공식 코드

Balanced Contrastive Learning for Long-Tailed Visual Recognition

https://github.com/fourierai/idea

공식 코드

IDEA: Image Description Enhanced CLIP-Adapter

https://github.com/frank-xwang/RIDE-LongTailRecognition

공식 코드

Long-tailed Recognition by Routing Diverse Distribution-Aware Experts

https://github.com/frank-xwang/debiased-pseudo-labeling

공식 코드

Debiased Learning from Naturally Imbalanced Pseudo-Labels

https://github.com/ganatra-v/gaussian-sampling-fsl

공식 코드

Logarithm-transform aided Gaussian Sampling for Few-Shot Learning

https://github.com/gaopengcuhk/ballad

공식 코드

A Simple Long-Tailed Recognition Baseline via Vision-Language Model

https://github.com/gidariss/FewShotWithoutForgetting

공식 코드

Dynamic Few-Shot Visual Learning without Forgetting

https://github.com/gmum/few-shot-hypernets-public

공식 코드

HyperShot: Few-Shot Learning by Kernel HyperNetworks

https://github.com/goldblum/AdversarialQuerying

공식 코드

Adversarially Robust Few-Shot Learning: A Meta-Learning Approach

https://github.com/google-research/big_vision

공식 코드

Scaling Vision Transformers

https://github.com/google-research/google-research

공식 코드

Class-Balanced Distillation for Long-Tailed Visual Recognition

https://github.com/google-research/google-research/tree/master/class_balanced_distillation

공식 코드

Class-Balanced Distillation for Long-Tailed Visual Recognition

https://github.com/google-research/google-research/tree/master/hypertransformer

공식 코드

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning

https://github.com/google-research/google-research/tree/master/logit_adjustment

공식 코드

Long-tail learning via logit adjustment

https://github.com/google-research/google-research/tree/master/meta_learning_without_memorization

공식 코드

Meta-Learning without Memorization

https://github.com/google-research/google-research/tree/master/muNet

공식 코드

A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems

https://github.com/google-research/meta-dataset

공식 코드

Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples

https://github.com/google-research/vmoe

공식 코드

Scaling Vision with Sparse Mixture of Experts

https://github.com/guliisgreat/orbit-2022-winner-method

공식 코드

Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

https://github.com/guodongqi/cmvae

공식 코드

CMVAE: Causal Meta VAE for Unsupervised Meta-Learning

https://github.com/hanlu-nju/revisiting-uml

공식 코드

Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks

https://github.com/heekhero/ACSR

공식 코드

Worst Case Matters for Few-Shot Recognition

https://github.com/hitachi-rd-cv/CDB-loss

공식 코드

Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance

https://github.com/hitachi-rd-cv/Difficulty_Net

공식 코드

Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition

https://github.com/hongguangzhang/mlso-tmm-master

공식 코드

Multi-level Second-order Few-shot Learning

https://github.com/huaxiuyao/ARML

공식 코드

Automated Relational Meta-learning

https://github.com/huaxiuyao/HSML

공식 코드

Hierarchically Structured Meta-learning

https://github.com/hushell/pmf_cvpr22

공식 코드

Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference

https://github.com/hushell/sib_meta_learn

공식 코드

Empirical Bayes Transductive Meta-Learning with Synthetic Gradients

https://github.com/hyperconnect/LADE

공식 코드

Disentangling Label Distribution for Long-tailed Visual Recognition

https://github.com/icgy96/micm

공식 코드

MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning

https://github.com/ihsaan-ullah/meta-album

공식 코드

Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification

https://github.com/ihsanullah2131/meta-album

공식 코드

Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification

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