PLANKTON CLASSIFICATION ON IMBALANCED LARGE SCALE DATABASE VIA CONVOLUTIONAL NEURAL NETWORKS WITH TRANSFER LEARNING

机译：通过转移学习的卷积神经网络分类对非衡度大规模数据库的浮游生物分类

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Plankton image classification plays an important role in the ocean ecosystems research. Recently, a large scale database for plankton classification with over 3 million images annotated with over 100 classes was released. However, the database suffers from imbalanced class distribution in which over 90% of images belong to only 5 classes. Due to this class-imbalance problem, the existing classification approaches are limited to label the data only to major classes, ignoring the small-sized classes. In this paper, we propose a fine-grained classification method for large scale plankton database based on convolutional neural networks (CNN). To overcome the class-imbalance problem, we incorporate transfer learning by pre-training CNN with class-normalized data and fine-tuning with original data. The class-normalized data is constructed by reducing the number of data via random sampling, for large-sized classes. In experiments, our method showed superior classification accuracy compared to both CNN without transfer learning and CNN with transfer learning via other data augmentation techniques.

机译：Plankton Image Classifications在海洋生态系统研究中起着重要作用。最近，释放了一个有超过100级课程的300多万图像的普拉克顿分类的大规模数据库。但是，数据库遭受了不平衡的类分布，其中超过90％的图像属于仅为5个类。由于这个类别不平衡问题，现有的分类方法仅限于将数据标记为主要类，忽略小型类。在本文中，我们提出了一种基于卷积神经网络（CNN）的大规模浮游生物数据库的细粒度分类方法。为了克服类别不平衡问题，我们通过预先训练CNN与类标准化的数据和具有原始数据进行微调的CNN进行转移学习。通过对大型类的随机采样减少数据数量来构建类归一化数据。在实验中，与通过其他数据增强技术的转移学习的情况显示，我们的方法显示出卓越的分类准确性和CNN。

著录项

来源
《IEEE International Conference on Image Processing》|2016年|3214-3856p|共5页
会议地点
作者
Hansang Lee; Minseok Park; Junmo Kim;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类 TP391.41-53;
关键词
Image classification; Plankton images; Transfer learning; Convolutional neural networks; Fine-grained classification;

机译：图像分类;浮游形象;转移学习;卷积神经网络;细粒度分类;

相似文献

外文文献
中文文献
专利

1. Application of Deep Convolutional Neural Networks in Attention-Deficit/Hyperactivity Disorder Classification: Data Augmentation and Convolutional Neural Network Transfer Learning [J] . Zhu Li, Chang Weike Journal of Medical Imaging and Health Informatics . 2019,第8期

机译：深度卷积神经网络在注意力缺陷/多动障碍分类中的应用：数据增强与卷积神经网络转移学习
2. A predictive machine learning application in agriculture: Cassava disease detection and classification with imbalanced dataset using convolutional neural networks [J] . G. Sambasivam, Geoffrey Duncan Opiyo Egyptian Informatics Journal . 2021,第1期

机译：采用卷积神经网络的预测机器学习申请：木薯病检测和对不平衡数据集的分类
3. AdaBoost-CNN: An adaptive boosting algorithm for convolutional neural networks to classify multi-class imbalanced datasets using transfer learning [J] . Taherkhani Aboozar, Cosma Georgina, McGinnity T. M. Neurocomputing . 2020,第Sepa3期

机译：adaboost-cnn：卷积神经网络的自适应促进算法，用于使用传输学习对多级不平衡数据集进行分类
4. Plankton classification on imbalanced large scale database via convolutional neural networks with transfer learning [C] . Hansang Lee, Minseok Park, Junmo Kim IEEE International Conference on Image Processing . 2016

机译：带有转移学习的卷积神经网络在不平衡大型数据库上的浮游生物分类
5. Plankton image classification using convolutional neural network. [D] . Al-barazanchi, Hussein Ali Kadhim. 2016

机译：使用卷积神经网络对浮游生物图像进行分类。
6. Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning [O] . Juan J. Gómez-Valverde, Alfonso Antón, Gianluca Fatti, 2019

机译：基于卷积神经网络和转移学习的彩色眼底图像自动青光眼分类
7. Transferring Ensemble Representations Using Deep Convolutional Neural Networks for Small-Scale Image Classification [O] . Shuyin Xia, Yulong Xia, Hong Yu, 2019

机译：使用深度卷积神经网络传输集合表示，用于小型图像分类

PLANKTON CLASSIFICATION ON IMBALANCED LARGE SCALE DATABASE VIA CONVOLUTIONAL NEURAL NETWORKS WITH TRANSFER LEARNING

摘要

著录项

相似文献

相关主题

期刊订阅