Class Rectification Hard Mining for Imbalanced Deep Learning

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.

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SMOTE: Synthetic Minority Over-sampling Technique
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Learning Deep Embeddings with Histogram Loss
• Unsupervised Learning of Visual Representations using Videos
• Deep Learning Face Attributes in the Wild
• Attribute Recognition by Joint Recurrent Learning of Context and Correlation
• Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop
• PANDA: Pose Aligned Networks for Deep Attribute Modeling
• Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes

Cited by in corpus (3)

• Dynamic Curriculum Learning for Imbalanced Data Classification
• Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
• On Class Imbalance and Background Filtering in Visual Relationship Detection