Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space

聚类分析 计算机科学 人工智能 模式识别(心理学) 图像(数学) 集合(抽象数据类型) 上下文图像分类 无监督学习 透视图(图形) 弹丸 可视化 机器学习 有机化学 化学 程序设计语言
作者
Shuo Li,Fang Liu,Zehua Hao,Kaibo Zhao,Licheng Jiao
标识
DOI:10.1007/978-3-031-19821-2_24
摘要

Most few-shot image classification methods are trained based on tasks. Usually, tasks are built on base classes with a large number of labeled images, which consumes large effort. Unsupervised few-shot image classification methods do not need labeled images, because they require tasks to be built on unlabeled images. In order to efficiently build tasks with unlabeled images, we propose a novel single-stage clustering method: Learning Features into Clustering Space (LF2CS), which first set a separable clustering space by fixing the clustering centers and then use a learnable model to learn features into the clustering space. Based on our LF2CS, we put forward an image sampling and c-way k-shot task building method. With this, we propose a novel unsupervised few-shot image classification method, which jointly learns the learnable model, clustering and few-shot image classification. Experiments and visualization show that our LF2CS has a strong ability to generalize to the novel categories. From the perspective of image sampling, we implement four baselines according to how to build tasks. We conduct experiments on the Omniglot, miniImageNet, tieredImageNet and CIFARFS datasets based on the Conv-4 and ResNet-12 backbones. Experimental results show that ours outperform the state-of-the-art methods.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
岁月如歌发布了新的文献求助10
刚刚
bin完成签到,获得积分10
2秒前
2秒前
很好完成签到,获得积分10
3秒前
小郝已读博完成签到 ,获得积分10
3秒前
3秒前
Self-made完成签到,获得积分10
3秒前
4秒前
5秒前
6秒前
岁月如歌完成签到,获得积分10
7秒前
8秒前
joey完成签到,获得积分10
9秒前
wei完成签到 ,获得积分10
10秒前
miaojuly发布了新的文献求助10
11秒前
11秒前
研友_LXjjOZ发布了新的文献求助150
11秒前
12秒前
13秒前
14秒前
坚定馒头完成签到,获得积分10
14秒前
15秒前
15秒前
星星应助科研通管家采纳,获得30
17秒前
y924758705完成签到,获得积分20
17秒前
打打应助科研通管家采纳,获得10
17秒前
坦率的匪应助科研通管家采纳,获得10
17秒前
烟花应助科研通管家采纳,获得10
17秒前
上官若男应助科研通管家采纳,获得10
17秒前
隐形曼青应助科研通管家采纳,获得10
17秒前
NexusExplorer应助科研通管家采纳,获得10
18秒前
18秒前
YamDaamCaa应助科研通管家采纳,获得30
18秒前
18秒前
18秒前
怡然乌应助科研通管家采纳,获得10
18秒前
18秒前
曹恺悦发布了新的文献求助30
19秒前
20秒前
20秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3988868
求助须知:如何正确求助?哪些是违规求助? 3531255
关于积分的说明 11253071
捐赠科研通 3269858
什么是DOI,文献DOI怎么找? 1804822
邀请新用户注册赠送积分活动 881994
科研通“疑难数据库(出版商)”最低求助积分说明 809035