两级分层特征提升图像分类精度：深度学习新策略
193 浏览量
更新于2024-08-27
收藏 695KB PDF 举报
本文主要探讨了在图像分类任务中，如何有效地解决类别间相似性差异导致的误分类问题。作者提出了一种新颖的两级分层特征学习框架，该框架结合了深度卷积神经网络（Deep Convolutional Neural Networks, DCNN）的迁移学习技术和层次分类的思想。迁移学习首先利用预训练的DCNN模型对新的目标数据集进行微调，以提取深层次的通用特征，这些特征能够捕捉到图像的基本结构和模式。
在分层特征学习的第二阶段，针对高度相似的类别，专门提取了更为具体的、针对性的特征。这一步可能涉及到使用特定的子网络或者特征选择技术，以增强对这些类别之间细微差别的识别能力。这些特定特征与一般特征融合后，构成了更全面的特征表示，用于线性分类器的输入，从而提高了分类的准确性。
文章强调，这种两级分层特征学习方法的优势在于它能够同时处理全局信息和局部细节，使得分类器能够在处理复杂类别关系时更加精确。通过实验，如在Caltech-256、Oxford Flower-102和Tasmanian Coral Point Count (CPC)等数据集上的测试，结果证明了这种方法的有效性。相比于传统的平面多重分类方法，两级分层特征学习显著提升了分类精度，特别是在处理那些类别间存在较高相似性的图像时。
此外，文章还可能讨论了特征融合的方法，比如可能是通过加权平均或者注意力机制来整合一般特征和特定特征。同时，可能也提到了谱聚类（Spectral Clustering）在特征选择或特征空间划分中的应用，帮助优化了特征表示。
本文的主要贡献在于提供了一个创新的策略，通过深度学习和层次结构设计，提高了图像分类任务的性能，尤其是在处理具有高相似性的类别时，显示出了其强大的特征表达能力和分类能力。
Song et al. / Front Inform Technol Electron Eng 2016 17(9):897-906 897
Frontiers of Information Technology & Electronic Engineering
www.zju.edu.cn/jzus; engineering.cae.cn; www.springerlink.com
ISSN 2095-9184 (print); ISSN 2095-9230 (online)
E-mail: jzus@zju.edu.cn
Two-level hierarchical feature learning for
image classification
∗
Guang-hui SONG
1,2
, Xiao-gang JIN
†‡1
,Gen-langCHEN
2
,YanNIE
3
(
1
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China)
(
2
Ningbo Institute of Technology, Zhejiang University, Ningb o 315100, China)
(
3
College of Science and Technology, Ningbo University, Ningb o 315100, China)
†
E-mail: xiaogangj@cise.zju.edu.cn
Received Oct. 20, 2015; Revision accepted Apr. 10, 2016; Crosschecked Aug. 8, 2016
Abstract: In some image classification tasks, similarities among different categories are different and the samples
are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features
are required so that the classifier can improve the classification performance. In this paper, we propose a novel
two-level hierarchical feature learning framework based on the deep convolutional neural network (CNN), which is
simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning
method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature
extracted from all the categories and the specific feature extracted from highly similar categories are fused into a
feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the
Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count (CPC) datasets demonstrate that the expression
ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method
effectively increases the classification accuracy in comparison with flat multiple classification methods.
Key words: Transfer learning, Feature learning, Deep convolutional neural network, Hierarchical classification,
Spectral clustering
http://dx.doi.org/10.1631/FITEE.1500346 CLC number: TP391.4
1 Introduction
The deep convolutional neural network (CNN)
has achieved impressive classification performance in
the ImageNet benchmark (Krizhevsky et al., 2012).
Surprisingly, transfer learning methods based on the
deep convolutional feature trained on a generic recog-
nition task are also successful in various computer
vision tasks, such as object classification, domain
adaptation, and scene recognition. They achieve
results superior to those of the previous meth-
‡
Corresponding author
*
Project supported by the National Natural Science Foundation
of China (No. 61379074) and the Zhejiang Provincial Natural Sci-
ence Foundation of China (Nos. LZ12F02003 and LY15F020035)
OR CID: Xiao-gang JIN, http://orcid.org/0000-0002-7787-7228
c
Zhejiang University and Springer-Verlag Berlin Heidelberg 2016
ods (Donahue et al., 2014; Zeiler and Fergus, 2014;
Cai et al., 2015). Therefore, the feature learning
ability of deep CNN has received considerable at-
tention. In previous studies, deep CNN models were
used as feature extractors but not as classifiers, and
they provided a way to obtain more specific visual
features (Yosinski et al., 2014).
At present, most deep CNN models serve as
flat end-to-end classifiers for image recognition tasks.
These deep models take the raw image as the network
input, extract image features using back-propagation
through layers of convolutional filters, and finally
output the categorized results using a softmax out-
put layer. However, the reality is that image datasets
have a growing sample size and image category. Simi-
larities are different among different categories, with
下载后可阅读完整内容，剩余9页未读，立即下载
2021-09-26 上传
2012-04-11 上传
2021-02-24 上传
2021-04-15 上传
2020-12-21 上传
2021-04-29 上传
2021-03-06 上传
2022-10-12 上传
点击了解资源详情
weixin_38614377
- 粉丝: 2
- 资源: 945
我的内容管理
展开
最新资源
- 火炬连体网络在MNIST的2D嵌入实现示例
- Angular插件增强Application Insights JavaScript SDK功能
- 实时三维重建：InfiniTAM的ros驱动应用
- Spring与Mybatis整合的配置与实践
- Vozy前端技术测试深入体验与模板参考
- React应用实现语音转文字功能介绍
- PHPMailer-6.6.4: PHP邮件收发类库的详细介绍
- Felineboard：为猫主人设计的交互式仪表板
- PGRFileManager：功能强大的开源Ajax文件管理器
- Pytest-Html定制测试报告与源代码封装教程
- Angular开发与部署指南：从创建到测试
- BASIC-BINARY-IPC系统：进程间通信的非阻塞接口
- LTK3D: Common Lisp中的基础3D图形实现
- Timer-Counter-Lister:官方源代码及更新发布
- Galaxia REST API：面向地球问题的解决方案
- Node.js模块：随机动物实例教程与源码解析
