Plant Identification with Deep Learning Ensembles

This work describes the plant identification system that we submitted to the ExpertLifeCLEF plant identification campaign in 2018. We fine-tuned two pre-trained deep learning architectures (SeNet and DensNetwork) using images shared by the CLEF organizers in 2017. Our main runs are 4 ensembles obtained with different weighted combinations of the 4 deep learning architectures. The fifth ensemble is based on deep learning features but uses Error Correcting Output Codes (ECOC) as the ensemble. Our best system has achieved a classification accuracy of 74.4%, while the best system obtained 86.7% accuracy, on the whole of the official test data. This system ranked 4th place among all the teams, but matched the accuracy of one of the human experts.

[1]  Pierre Bonnet,et al.  Overview of ExpertLifeCLEF 2018: how far Automated Identification Systems are from the Best Experts? , 2018, CLEF.

[2]  Ethem Alpaydin,et al.  FLIP-ECOC: A Greedy Optimization of the ECOC Matrix , 2010, ISCIS.

[3]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[5]  Josef Kittler,et al.  BeamECOC: A local search for the optimization of the ECOC matrix , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[6]  Alexis Joly,et al.  LifeCLEF Plant Identification Task 2014 , 2014, CLEF.

[7]  Pierre Bonnet,et al.  Plant Identification Based on Noisy Web Data: the Amazing Performance of Deep Learning (LifeCLEF 2017) , 2017, CLEF.

[8]  Mostafa Mehdipour-Ghazi,et al.  Open-set Plant Identification Using an Ensemble of Deep Convolutional Neural Networks , 2016, CLEF.

[9]  Berrin A. Yanikoglu,et al.  Sabanci-Okan System at ImageClef 2011: Plant Identification Task , 2011, CLEF.

[10]  Berrin A. Yanikoglu,et al.  Sabanci-Okan System at ImageClef 2012: Combining Features and Classifiers for Plant Identification , 2012, CLEF.

[11]  Hervé Glotin,et al.  Overview of LifeCLEF 2018: A Large-Scale Evaluation of Species Identification and Recommendation Algorithms in the Era of AI , 2018, CLEF.

[12]  Pierre Bonnet,et al.  Plant Identification in an Open-world (LifeCLEF 2016) , 2016, CLEF.

[13]  Thomas G. Dietterich,et al.  Solving Multiclass Learning Problems via Error-Correcting Output Codes , 1994, J. Artif. Intell. Res..

[14]  Nozha Boujemaa,et al.  The ImageCLEF 2012 Plant Identification Task , 2012, CLEF.

[15]  Mostafa Mehdipour-Ghazi,et al.  Plant identification using deep neural networks via optimization of transfer learning parameters , 2017, Neurocomputing.

[16]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Nozha Boujemaa,et al.  The CLEF 2011 Plant Images Classification Task , 2011, CLEF.

[19]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.