Modelling local deep convolutional neural network features to improve fine-grained image classification

Loading...
Thumbnail Image
File version

Accepted Manuscript (AM)

Author(s)
Ge, ZongYuan
McCool, Chris
Sanderson, Conrad
Corke, Peter
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
2015
Size
File type(s)
Location

Quebec City, Canada

License
Abstract

We propose a local modelling approach using deep convolutional neural networks (CNNs) for fine-grained image classification. Recently, deep CNNs trained from large datasets have considerably improved the performance of object recognition. However, to date there has been limited work using these deep CNNs as local feature extractors. This partly stems from CNNs having internal representations which are high dimensional, thereby making such representations difficult to model using stochastic models. To overcome this issue, we propose to reduce the dimensionality of one of the internal fully connected layers, in conjunction with layer-restricted retraining to avoid retraining the entire network. The distribution of low-dimensional features obtained from the modified layer is then modelled using a Gaussian mixture model. Comparative experiments show that considerable performance improvements can be achieved on the challenging Fish and UEC FOOD-100 datasets.

Journal Title
Conference Title

Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP)

Book Title
Edition
Volume
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement

© 2015 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.

Item Access Status
Note
Access the data
Related item(s)
Subject

Image processing

Persistent link to this record
Citation

Ge, Z; McCool, C; Sanderson, C; Corke, P, Modelling local deep convolutional neural network features to improve fine-grained image classification, 2015 IEEE International Conference on Image Processing (ICIP), 2015, pp. 4112-4116