Skip to main content

Deep Bottleneck Feature for Image Classification

Song, Yan and McLoughlin, Ian and Dai, Lirong (2015) Deep Bottleneck Feature for Image Classification. In: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval. MM International Multimedia Conference . ACM, New York, USA, pp. 491-494. ISBN 978-1-4503-3274-3. (doi:10.1145/2671188.2749314) (KAR id:55018)

PDF Publisher pdf
Language: English

Download (971kB)
[thumbnail of p491-song.pdf]
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL:


Effective image representation plays an important role for image classification and retrieval. Bag-of-Features (BoF) is well known as an effective and robust visual representation. However, on large datasets, convolutional neural networks (CNN) tend to perform much better, aided by the availability of large amounts of training data. In this paper, we propose a bag of Deep Bottleneck Features (DBF) for image classification, effectively combining the strengths of a CNN within a BoF framework. The DBF features, obtained from a previously well-trained CNN, form a compact and low-dimensional representation of the original inputs, effective for even small datasets. We will demonstrate that the resulting BoDBF method has a very powerful and discriminative capability that is generalisable to other image classification tasks.

Item Type: Book section
DOI/Identification number: 10.1145/2671188.2749314
Uncontrolled keywords: Image Classification; Transfer Learning; BoF; CNN;
Subjects: T Technology
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Ian McLoughlin
Date Deposited: 19 Apr 2016 09:55 UTC
Last Modified: 08 Dec 2022 23:17 UTC
Resource URI: (The current URI for this page, for reference purposes)
McLoughlin, Ian:
  • Depositors only (login required):


Downloads per month over past year