PK PyTorchKR Papers
Papers with Code 아카이브

Few-Shot Image Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 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>

평가 결과

데이터셋과 평가 조건을 선택해 성능·논문·코드를 비교하세요. 보존된 Papers with Code 기록으로, 최신 순위는 아닙니다.

ImageNet-LT

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 69건

CIFAR-100-LT (ρ=100)

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 66건

CIFAR-10-LT (ρ=10)

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 50건

iNaturalist 2018

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 43건

CIFAR-100-LT (ρ=10)

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 31건

Places-LT

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 29건

CIFAR-10-LT (ρ=100)

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 28건

Mini-Imagenet 5-way (1-shot)

원본 태스크: Few-Shot Image Classification / Unsupervised Few-Shot Image Classification

평가 기록 28건

Mini-Imagenet 5-way (5-shot)

원본 태스크: Few-Shot Image Classification / Unsupervised Few-Shot Image Classification

평가 기록 28건

CIFAR-100-LT (ρ=50)

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 25건

Meta-Dataset

원본 태스크: Few-Shot Image Classification

평가 기록 22건

MIMIC-CXR-LT

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 15건

NIH-CXR-LT

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 15건

COCO-MLT

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 13건

Meta-Dataset Rank

원본 태스크: Few-Shot Image Classification

평가 기록 13건

VOC-MLT

원본 태스크: Few-Shot Image Classification / Generalized Few-Shot Classification / Long-tail Learning

평가 기록 13건

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