Few-shot classification and few-shot fine-grained classification datasets

Name: Few-shot classification and few-shot fine-grained classification datasets
Creator: Zhixiong Leng
Published: 2026-04-17T17:24:54+08:00

IEEE2026-04-17 收录

少样本学习

细粒度分类

数据链接：

https://ieee-dataport.org/documents/few-shot-classification-and-few-shot-fine-grained-classification-datasets 数据链接链接失效反馈

官方服务：

资源简介：

miniImageNet; CIFAR-FS; Aircraft; Dogs

提供机构：

In this work, we build a new food image dataset FoodSeg103 (and its extension FoodSeg154) containing 9,490 images. We annotate these images with 154 ingredient classes and result in an average of 6 in

larc.smu.edu.sg940

Multimodal-Fatima/OxfordPets_test_facebook_opt_6.7b_Visclues_ns_3669_random

细粒度分类

语言模型评估

--- dataset_info: features: - name: id dtype: int64 - name: image dtype: image - name: prompt dtype: string - name: true_label dtype: string - name: prediction dtype: s

Hugging Face2023-02-06 更新200

Data from: An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning

少样本学习

图像分类

PyTorch implementation of "An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning" This repository contains the PyTorch implementation for the ECCV 2020 Paper "An Ensemble of Epoch-wise Empi

NIAID Data Ecosystem70

FEW-NERD

实体识别

少样本学习

FEW-NERD是一个大规模的人工标注少样本命名实体识别数据集，由清华大学和阿里巴巴集团合作创建。该数据集包含188,238个句子，总计4,601,160个单词，每个单词都被标注为上下文或两级实体类型的一部分。FEW-NERD是首个专门为少样本NER设计的数据集，也是最大的人工标注NER数据集之一。数据集的内容主要来源于维基百科，涵盖了8个粗粒度和66个细粒度实体类型，旨在通过丰富的实体类型和上下

arXiv2021-09-01 更新450

FSS-1000: A 1000 Class Few-shot Segmentation

少样本学习

影像分割

10 images along with segmentation masks per each of 1000 classes

kaggle2021-10-31 更新110