Fine-grained classification via mixture of deep convolutional neural networks

Zongyuan Ge, Alex Bewley, Christopher McCool, Peter Corke, Ben Upcroft, Conrad Sanderson

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

37 Citations (Scopus)


We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7% and achieves state-of-the-art results on two datasets.

Original languageEnglish
Title of host publication2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016)
EditorsGreg Mori, Robert Pless, Scott McCloskey, Rahul Sukthankar
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)9781509006410
ISBN (Print)9781509006427
Publication statusPublished - 23 May 2016
Externally publishedYes
EventIEEE Winter Conference on Applications of Computer Vision 2016 - Lake Placid, United States of America
Duration: 7 Mar 201610 Mar 2016 (Proceedings)


ConferenceIEEE Winter Conference on Applications of Computer Vision 2016
Abbreviated titleWACV 2016
Country/TerritoryUnited States of America
CityLake Placid
Internet address

Cite this