University of Oulu

J. Liang, J. Guo, X. Liu and S. Lao, "Fine-Grained Image Classification With Gaussian Mixture Layer," in IEEE Access, vol. 6, pp. 53356-53367, 2018. doi: 10.1109/ACCESS.2018.2871621

Fine-grained image classification with Gaussian mixture layer

Saved in:
Author: Liang, Jingyun1; Guo, Jinlin1; Liu, Xin2;
Organizations: 1College of System Engineering, National University of Defense Technology, Changsha, China
2Computer Science and Engineering Department, University of Oulu, Oulu, Finland
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 1.8 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2018112048690
Language: English
Published: Institute of Electrical and Electronics Engineers, 2018
Publish Date: 2018-11-20
Description:

Abstract

Fine-grained image classification aims at recognizing different subordinates in one basic-level category, for example, distinguishing species of birds. Compared with basic-level classification, it has both low inter-class and high intra-class variances. Therefore, utilization of discriminative parts is crucial for fine-grained classification. In this paper, we propose a Gaussian mixture model, which fuses part features by Gaussian mixture layer. More specifically, it first generates a set of part proposals by selective search. Then, we extract image feature maps from mid-layers of convolutional neural networks. Feature maps and part proposals are used for calculating part features via spatial pyramid pooling. Next, Gaussian mixture layer treats part features as data points and uses several Gaussian components to model their distribution. It finds clusters for input and generates output features based on combination of cluster center. Finally, the output feature can represent the whole image and is used for classification. Training process of the model consists of two loops. The outer loop is the optimization of the whole network, and the inner loop is about the EM algorithm used in Gaussian mixture layer. Experiments demonstrate higher or similar performance on four fine-grained data sets compared with the state-of-the-arts. More discussions on Gaussian mixture layer are also provided.

see all

Series: IEEE access
ISSN: 2169-3536
ISSN-E: 2169-3536
ISSN-L: 2169-3536
Volume: 6
Pages: 53356 - 53367
DOI: 10.1109/ACCESS.2018.2871621
OADOI: https://oadoi.org/10.1109/ACCESS.2018.2871621
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Subjects:
Funding: This work was supported by the National Natural Science Foundation of China under Project 61571453.
Copyright information: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.