Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation

In particular, the lack of sufficient amounts of domain-specific data can reduce the accuracy of a classifier. In this paper, we explore the effects of style transfer-based data transformation on the accuracy of a convolutional neural network classifiers in the context of automobile detection under adverse winter weather conditions. The detection of automobiles under highly adverse weather conditions is a difficult task as such conditions present large amounts of noise in each image. The InceptionV2 architecture is trained on a composite dataset, consisting of either normal car image dataset , a mixture of normal and style transferred car images, or a mixture of normal car images and those taken at blizzard conditions, at a ratio of 80:20. All three classifiers are then tested on a dataset of car images taken at blizzard conditions and on vehicle-free snow landscape images. We evaluate and contrast the effectiveness of each classifier upon each dataset, and discuss the strengths and weaknesses of style-transfer based approaches to data augmentation.

[1]  Weihong Deng,et al.  Very deep convolutional neural network based image classification using small training sample size , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

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

[3]  Aljosa Smolic,et al.  STaDA: Style Transfer as Data Augmentation , 2019, VISIGRAPP.

[4]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[5]  Hui Li,et al.  Digital mammographic tumor classification using transfer learning from deep convolutional neural networks , 2016, Journal of medical imaging.

[6]  Toby P. Breckon,et al.  Style Augmentation: Data Augmentation via Style Randomization , 2018, CVPR Workshops.

[7]  Thomas Brox,et al.  Sparsity Invariant CNNs , 2017, 2017 International Conference on 3D Vision (3DV).

[8]  Ling Shao,et al.  Transfer Learning for Visual Categorization: A Survey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[10]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[11]  Andreas Geiger,et al.  Augmented Reality meets Deep Learning , 2017, BMVC.

[12]  David Zhang,et al.  Robust Visual Knowledge Transfer via Extreme Learning Machine-Based Domain Adaptation , 2016, IEEE Transactions on Image Processing.

[13]  Leon A. Gatys,et al.  A Neural Algorithm of Artistic Style , 2015, ArXiv.

[14]  Shengen Yan,et al.  Deep Image: Scaling up Image Recognition , 2015, ArXiv.

[15]  Shiguo Lian,et al.  A survey on face data augmentation for the training of deep neural networks , 2019, Neural Computing and Applications.

[16]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[17]  Liang Chen,et al.  GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks , 2018, ArXiv.

[18]  Gabriela Csurka,et al.  Domain Adaptation for Visual Applications: A Comprehensive Survey , 2017, ArXiv.

[19]  Saumik Bhattacharya,et al.  Effects of Degradations on Deep Neural Network Architectures , 2018, ArXiv.

[20]  Claus Aranha,et al.  Data Augmentation Using GANs , 2019, ArXiv.

[21]  Jiaying Liu,et al.  Demystifying Neural Style Transfer , 2017, IJCAI.