Generally Boosting Few-Shot Learning with HandCrafted Features

Boosting(机器学习) 计算机科学 弹丸 人工智能 一次性 机器学习
作者
Yi Zhang,Sheng Huang,Fengtao Zhou
出处
期刊: [Association for Computing Machinery]
卷期号:: 3143-3152 被引量:6
标识
DOI:10.1145/3474085.3475459
摘要

Existing Few-Shot Learning (FSL) methods predominantly focus on developing different types of sophisticated models to extract the transferable prior knowledge for recognizing novel classes, while they almost pay less attention to the feature learning part in FSL which often simply leverage some well-known CNN as the feature learner. However, feature is the core medium for encoding such transferable knowledge. Feature learning is easy to be trapped in the over-fitting particularly in the scarcity of the training data, and thereby degenerates the performances of FSL. The handcrafted features, such as Histogram of Oriented Gradient (HOG) and Local Binary Pattern (LBP), have no requirement on the amount of training data, and used to perform quite well in many small-scale data scenarios, since their extractions involve no learning process, and are mainly based on the empirically observed and summarized prior feature engineering knowledge. In this paper, we intend to develop a general and simple approach for generally boosting FSL via exploiting such prior knowledge in the feature learning phase. To this end, we introduce two novel handcrafted feature regression modules, namely HOG and LBP regression, to the feature learning parts of deep learning-based FSL models. These two modules are separately plugged into the different convolutional layers of backbone based on the characteristics of the corresponding handcrafted features to guide the backbone optimization from different feature granularity, and also ensure that the learned feature can encode the handcrafted feature knowledge which improves the generalization ability of feature and alleviate the over-fitting of the models. Three recent state-of-the-art FSL approaches are leveraged for examining the effectiveness of our method. Extensive experiments on miniImageNet, CIFAR-FS and FC100 datasets show that the performances of all these FSL approaches are well boosted via applying our method on all three datasets. Our codes and models have been released.

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
刚刚
顾金铄完成签到,获得积分10
刚刚
缪缪拿铁完成签到,获得积分10
1秒前
1秒前
南歪歪完成签到,获得积分10
1秒前
悲凉的幻儿完成签到 ,获得积分10
1秒前
阿俞的应助被00hello00采纳,获得10
3秒前
4秒前
4秒前
感动的水风完成签到,获得积分10
5秒前
5秒前
jiajia发布了新的文献求助10
6秒前
肥泉的应助被李大侠采纳,获得10
6秒前
6秒前
uu完成签到,获得积分10
7秒前
8秒前
Akim的应助被111采纳,获得10
8秒前
8秒前
突金塔克树完成签到,获得积分10
8秒前
9秒前
称心青亦发布了新的文献求助10
9秒前
10秒前
搜集达人的应助被Ming采纳,获得10
10秒前
isukini发布了新的文献求助10
10秒前
uu发布了新的文献求助10
10秒前
11秒前
renn发布了新的文献求助10
11秒前
尊敬盼望完成签到 ,获得积分10
11秒前
aaa发布了新的文献求助10
12秒前
13秒前
老温完成签到,获得积分10
13秒前
13秒前
13秒前
GU发布了新的文献求助10
13秒前
小五完成签到,获得积分10
14秒前
ljq发布了新的文献求助10
14秒前
14秒前
00hello00发布了新的文献求助10
14秒前
汉堡包的应助被cfw采纳,获得10
14秒前
852的应助被beyondh采纳,获得10
15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