Feature learning via mixtures of DCNNs for fine-grained plant classification

Chris McCool, ZongYuan Ge, Peter Corke

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

1 Citation (Scopus)


We present the plant classification system submitted by the QUT RV team to the LifeCLEF 2016 plant task. Our system learns two deep convolutional neural network models. The first is a domain-specific model and the second is a mixture of content specific models, one for each of the plant organs such as branch, leaf, fruit, ower and stem. We combine these two models and experiments on the PlantCLEF2016 dataset show that this approach provides an improvement over the baseline system with the mean average precision improving from 0:603 to 0:629 on the test set.

Original languageEnglish
Title of host publicationCLEF 2016
Subtitle of host publicationCLEF2016 Working Notes
EditorsKrisztian Balog, Linda Cappellato, Nicola Ferro, Craig Macdonald
Place of PublicationAachen Germany
PublisherRWTH Aachen University
Number of pages7
Publication statusPublished - 1 Jan 2016
Externally publishedYes
Event Conference and Labs of the Evaluation Forum 2016: Information Access Evaluation meets Multilinguality, Multimodality and Interaction - University of Évora, Evora, Portugal
Duration: 5 Sep 20168 Sep 2016
Conference number: 7th

Publication series

NameCEUR Workshop Proceedings
PublisherRheinisch-Westfaelische Technische Hochschule Aachen * Lehrstuhl Informatik V
ISSN (Print)1613-0073


Conference Conference and Labs of the Evaluation Forum 2016
Abbreviated titleCLEF 2016
Internet address


  • Deep Convolutional Neural Network
  • Mixture Of Deep Convolutional Neural Networks
  • Plant Classification

Cite this