Class Rectification Hard Mining for Imbalanced Deep Learning

Qi Dong, Shaogang Gong, Xiatian Zhu; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1851-1860

Abstract


Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes. To address this problem, we formulate a novel scheme for batch incremental hard sample mining of minority attribute classes from imbalanced large scale training data. We develop an end-to-end deep learning framework capable of avoiding the dominant effect of majority classes by discovering sparsely sampled boundaries of minority classes. This is made possible by introducing a Class Rectification Loss (CRL) regularising algorithm. We demonstrate the advantages and scalability of CRL over existing state-of-the-art attribute recognition and imbalanced data learning models on two large scale imbalanced benchmark datasets, the CelebA facial attribute dataset and the X-Domain clothing attribute dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Dong_2017_ICCV,
author = {Dong, Qi and Gong, Shaogang and Zhu, Xiatian},
title = {Class Rectification Hard Mining for Imbalanced Deep Learning},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}