A Survey on Deep Learning-based Fine-grained Object Classification and Semantic Segmentation

被引：2

作者：

Bo Zhao ^{[1
,2
]}

Jiashi Feng ^{[2
]}

Xiao Wu ^{[1
]}

Shuicheng Yan ^{[2
]}

机构：

[1] School of Information Science and Technology,Southwest Jiaotong University

[2] Department of Electrical and Computer Engineering,National University of Singapore

来源：

International Journal of Automation and Computing | 2017年 / 14卷 / 02期

关键词：

Deep learning; fine-grained image classification; semantic segmentation; convolutional neural network(CNN); recurrent neural network(RNN);

D O I：

暂无

中图分类号：

TP391.41 []; TP183 [人工神经网络与计算];

学科分类号：

080203 ; 081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories, such as bird species or dog breeds. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we review four types of deep learning based fine-grained image classification approaches, including the general convolutional neural networks(CNNs), part detection based,ensemble of networks based and visual attention based fine-grained image classification approaches. Besides, the deep learning based semantic segmentation approaches are also covered in this paper. The region proposal based and fully convolutional networks based approaches for semantic segmentation are introduced respectively.

引用

页码：119 / 135

页数：17

共 6 条

[1]

Minimal Gated Unit for Recurrent Neural Networks[J]. Guo-Bing Zhou,Jianxin Wu,Chen-Lin Zhang,Zhi-Hua Zhou.International Journal of Automation and Computing. 2016(03)

[2] Feature Selection and Feature Learning for High-dimensional Batch Reinforcement Learning: A Survey [J].