Same Same but Different: Augmentation of Tiny Industrial Datasets using Generative Adversarial Networks

The evolution of generative adversarial networks has permitted the generation of realistic fake images which, in some cases, are indistinguishable from the real ones. Many recent works in image generation focus on learning internal image statistics via training only on a single natural image. While natural images exhibit a variability in their attributes, industrial images are often acquired in a controlled environment following a specific structure. In this work we utilize the cutting-edge results of single image generation on the structured case of industrial images. Deep Learning plays an important role in Industry 4.0 manufacturing lines and multiple ML-based image processing products are currently on the market. To be able to tackle a variety of problems where image acquisition is costly and time-consuming data generation is a promising approach. The proposed method only requires a handful of images for training, making it an ideal candidate for industrial application where data is scarce and confidential. It provides the foundation for a variety of use cases in the field of industrial Deep Learning.

[1]  Michal Irani,et al.  InGAN: Capturing and Retargeting the “DNA” of a Natural Image , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[2]  Taesung Park,et al.  Semantic Image Synthesis With Spatially-Adaptive Normalization , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Xiaogang Wang,et al.  StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Alexia Jolicoeur-Martineau,et al.  The relativistic discriminator: a key element missing from standard GAN , 2018, ICLR.

[5]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[6]  Martial Hebert,et al.  Low-Shot Learning from Imaginary Data , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Bernt Schiele,et al.  Not Using the Car to See the Sidewalk — Quantifying and Controlling the Effects of Context in Classification and Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Hayit Greenspan,et al.  GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification , 2018, Neurocomputing.

[9]  Takeru Miyato,et al.  cGANs with Projection Discriminator , 2018, ICLR.

[10]  Tali Dekel,et al.  SinGAN: Learning a Generative Model From a Single Natural Image , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  Zhe Gan,et al.  AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Amos J. Storkey,et al.  Data Augmentation Generative Adversarial Networks , 2017, ICLR 2018.

[13]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[14]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[15]  Dimitris N. Metaxas,et al.  StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[16]  Pietro Perona,et al.  Recognition in Terra Incognita , 2018, ECCV.

[17]  Li Fei-Fei,et al.  Image Generation from Scene Graphs , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Timo Aila,et al.  A Style-Based Generator Architecture for Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[20]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Lior Wolf,et al.  Specifying Object Attributes and Relations in Interactive Scene Generation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[22]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[23]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[24]  Jan Kautz,et al.  High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  Xiaohua Zhai,et al.  The Visual Task Adaptation Benchmark , 2019, ArXiv.

[26]  Seong Joon Oh,et al.  CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[27]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.