AdaTransform: Adaptive Data Transformation

Data augmentation is widely used to increase data variance in training deep neural networks. However, previous methods require either comprehensive domain knowledge or high computational cost. Can we learn data transformation automatically and efficiently with limited domain knowledge? Furthermore, can we leverage data transformation to improve not only network training but also network testing? In this work, we propose adaptive data transformation to achieve the two goals. The AdaTransform can increase data variance in training and decrease data variance in testing. Experiments on different tasks prove that it can improve generalization performance.

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

[2]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[3]  Quoc V. Le,et al.  AutoAugment: Learning Augmentation Policies from Data , 2018, ArXiv.

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

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

[6]  Fei Yang,et al.  Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Xi Peng,et al.  A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Christian Szegedy,et al.  DeepPose: Human Pose Estimation via Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Christopher Ré,et al.  Learning to Compose Domain-Specific Transformations for Data Augmentation , 2017, NIPS.

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

[11]  Mark Everingham,et al.  Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation , 2010, BMVC.

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

[13]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[14]  Jitendra Malik,et al.  Human Pose Estimation with Iterative Error Feedback , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Fernando De la Torre,et al.  Supervised Descent Method and Its Applications to Face Alignment , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

[17]  Abhinav Gupta,et al.  Training Region-Based Object Detectors with Online Hard Example Mining , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Bernt Schiele,et al.  2D Human Pose Estimation: New Benchmark and State of the Art Analysis , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Takuya Akiba,et al.  Shakedrop Regularization for Deep Residual Learning , 2018, IEEE Access.

[20]  Quoc V. Le,et al.  Efficient Neural Architecture Search via Parameter Sharing , 2018, ICML.

[21]  Stefanos Zafeiriou,et al.  300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[22]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

[23]  Alexei A. Efros,et al.  Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[24]  Xiaoou Tang,et al.  Facial Landmark Detection by Deep Multi-task Learning , 2014, ECCV.

[25]  George Trigeorgis,et al.  The Menpo Facial Landmark Localisation Challenge: A Step Towards the Solution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[26]  Cheng Cheng,et al.  A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Varun Ramakrishna,et al.  Convolutional Pose Machines , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Jia Deng,et al.  Stacked Hourglass Networks for Human Pose Estimation , 2016, ECCV.

[29]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[30]  Graham W. Taylor,et al.  Improved Regularization of Convolutional Neural Networks with Cutout , 2017, ArXiv.

[31]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[32]  Baoyuan Wu,et al.  Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Jonathan Tompson,et al.  Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation , 2014, NIPS.

[34]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[35]  Abhinav Gupta,et al.  A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Rogério Schmidt Feris,et al.  Delta-encoder: an effective sample synthesis method for few-shot object recognition , 2018, NeurIPS.