IFSM: An Iterative Feature Selection Mechanism for Few-Shot Image Classification

作者
Chunhao Cai,Minglei Yuan,Tong Lü
出处
期刊: [Institute of Electrical and Electronics Engineers]
卷期号:: 9429-9436 被引量:5
标识
DOI:10.1109/icpr48806.2021.9412864
摘要

Nowadays many deep learning algorithms have been employed to solve different types of problems in the area of computer vision; however, most of them require a great amount of training data and tend to struggle in few-shot learning tasks. On the other hand, those methods designed for few-shot learning usually face the difficulty that once one or more samples show a relatively large bias, the predicted result may be much less reliable due to the fact that the sample will cause a large shift of class-level features during few-shot learning. To solve this problem, this paper presents a novel and Iterative Feature Selection Mechanism (IFSM) for few-shot image classification, which can be applied to lots of metric-based few-shot learners. IFSM learns to construct a more feasible class-level feature which is less affected by samples with relatively large biases, using an iterative approach. The proposed mechanism is tested on three previous state-of-the-art few-shot learning methods, and the experimental results show that the proposed mechanism considerably improves (by 1% to 2%) the image classification accuracies of both methods on the miniImageNet, tieredImageNet or CUB benchmarks in 5-way 5-shot tasks. This approves the effectiveness and generality of the proposed mechanism.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
banana的应助被Ted采纳,获得10
刚刚
王浩发布了新的文献求助10
1秒前
王浩发布了新的文献求助10
1秒前
1秒前
1秒前
王浩发布了新的文献求助10
1秒前
王浩发布了新的文献求助10
1秒前
ding的应助被初初初啊采纳,获得10
2秒前
王浩发布了新的文献求助30
2秒前
2秒前
李爱国的应助被豪123456采纳,获得10
2秒前
2秒前
bobo完成签到,获得积分10
3秒前
安详慕卉完成签到,获得积分10
3秒前
sunyiyuan完成签到,获得积分10
3秒前
4秒前
王浩发布了新的文献求助10
4秒前
小研家发布了新的文献求助10
4秒前
隐形曼青的应助被xftx采纳,获得10
4秒前
5秒前
烟花的应助被活泼的鼠标采纳,获得10
5秒前
NexusExplorer的应助被修利采纳,获得10
5秒前
王浩发布了新的文献求助10
5秒前
6秒前
王浩发布了新的文献求助10
6秒前
王浩发布了新的文献求助10
6秒前
王浩发布了新的文献求助10
6秒前
王浩发布了新的文献求助10
7秒前
7秒前
8秒前
丸子完成签到,获得积分10
8秒前
8秒前
王浩发布了新的文献求助30
9秒前
王浩发布了新的文献求助10
9秒前
初景的应助被钟JUAN采纳,获得20
11秒前
12秒前
12秒前
13秒前
Happy发布了新的文献求助10
13秒前
精明一寡发布了新的文献求助10
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183923
求助须知:如何正确求助?哪些是违规求助? 9573132
关于积分的说明 21829461
捐赠科研通 7781024
什么是DOI,文献DOI怎么找? 3434150
关于科研通互助平台的介绍 2558333
邀请新用户注册赠送积分活动 2480648