Multi-label Learning on Image data has been widely exploited with deep learning models. However, supervised training on deep CNN models often cannot discover sufficient discriminative features for classification. As a result, numerous self-supervision methods are proposed to learn more robust image representations. However, most self-supervised approaches focus on single-instance single-label data and fall short on more complex images with multiple objects. Therefore, we propose an Object-Aware Self-Supervision (OASS) method to obtain more fine-grained representations for multi-label learning, dynamically generating auxiliary tasks based on object locations. Secondly, the robust representation learned by OASS can be leveraged to efficiently generate Class-Specific Instances (CSI) in a proposal-free fashion to better guide multi-label supervision signal transfer to instances. Extensive experiments on the VOC2012 dataset for multi-label classification demonstrate the effectiveness of the proposed method against the state-of-the-art counterparts.
@article{arxiv.2205.07028,
title = {Object-Aware Self-supervised Multi-Label Learning},
author = {Xu Kaixin and Liu Liyang and Zhao Ziyuan and Zeng Zeng and Bharadwaj Veeravalli},
journal= {arXiv preprint arXiv:2205.07028},
year = {2022}
}
Comments
Accepted by IEEE International Conference on Image Processing (ICIP 2022)