Mini Neural Networks for Effective and Efficient Mobile Album Organization

In this paper, we present an auto mobile album organization system, which can automatically classify daily photos in mobile devices into six daily categories, e.g., Baby, Food, Party, Scenery, Selfie, and Sport. Recently, deep convolutional neural networks have been used to build powerful classifiers by learning high-level representations of images. However, such models are limited to be implemented in the mobile album organization system due to the computational complexity of these networks with millions of parameters. To address these problems, we propose Mini Neural Networks (MiniNN) customized for mobile devices to improve computational efficiency of the album organization system, which is not sacrificed for performance a lot. We train the MiniNN model on the collected datasets as the classifier. Users can choose photos of any size as the input to the system, which will return the predicted tags. Experimental results show that the proposed MiniNN have an advantage over the CaffeNet with comparable classification accuracy but high computational efficiency. It can help us to organize daily photos in the mobile devices effectively and efficiently.

[1]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[2]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[3]  Camille Couprie,et al.  Learning Hierarchical Features for Scene Labeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Dong Yu,et al.  Conversational Speech Transcription Using Context-Dependent Deep Neural Networks , 2012, ICML.

[5]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[7]  Jinhui Tang,et al.  Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains , 2016, ACM Trans. Multim. Comput. Commun. Appl..

[8]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Luca Maria Gambardella,et al.  Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images , 2012, NIPS.

[10]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

[13]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[14]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[15]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[16]  Shuicheng Yan,et al.  Image Classification With Tailored Fine-Grained Dictionaries , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

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

[18]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[19]  Hanjiang Lai,et al.  Personalized Age Progression with Aging Dictionary , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[20]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[21]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.