Class Rectification Hard Mining for Imbalanced Deep Learning
This addresses attribute recognition in computer vision for applications like facial analysis or fashion, but it is incremental as it builds on existing imbalanced data learning methods.
The paper tackles the problem of recognizing detailed facial or clothing attributes from imbalanced large-scale training data by introducing a Class Rectification Loss (CRL) regularizing algorithm, which improves performance over state-of-the-art models on benchmarks like CelebA and X-Domain datasets.
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.