Attributes for Improved Attributes: A Multi-Task Network for Attribute Classification

Abstract

Attributes, or semantic features, have gained popularity in the past few years in domains ranging from activity recognition in video to face verification. Improving the accuracy of attribute classifiers is an important first step in any application which uses these attributes. In most works to date, attributes have been considered to be independent. However, we know this not to be the case. Many attributes are very strongly related, such as heavy makeup and wearing lipstick. We propose to take advantage of attribute relationships in three ways: by using a multi-task deep convolutional neural network (MCNN) sharing the lowest layers amongst all attributes, sharing the higher layers for related attributes, and by building an auxiliary network on top of the MCNN which utilizes the scores from all attributes to improve the final classification of each attribute. We demonstrate the effectiveness of our method by producing results on two challenging publicly available datasets.

References in corpus (2)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Deeply learned face representations are sparse, selective, and robust

Cited by in corpus (5)

• Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study
• A Deep Multi-task Learning Approach to Skin Lesion Classification
• Multi-task Learning of Cascaded CNN for Facial Attribute Classification
• Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification
• 3D-Aided Data Augmentation for Robust Face Understanding