AdaTransform: Adaptive Data Transformation

Zhiqiang Tang, Xi Peng, Tingfeng Li, Yizhe Zhu, Dimitris N. Metaxas; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 2998-3006

Abstract


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.

Related Material


[pdf]
[bibtex]
@InProceedings{Tang_2019_ICCV,
author = {Tang, Zhiqiang and Peng, Xi and Li, Tingfeng and Zhu, Yizhe and Metaxas, Dimitris N.},
title = {AdaTransform: Adaptive Data Transformation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}