Weakly-Supervised Online Hashing with Refined Pseudo Tags

Chen-Lu Ding, Xin Luo, Xiao-Ming Wu, Yu-Wei Zhan, Rui Li, Hui Zhang, Xin-Shun Xu

Abstract: With the rapid development of social media, various types of tags uploaded by social users are attached to the images. Compared to clean labels marked by experts, although user-provided tags are imperfect, e.g., wrong tags, reduplicative tags, or missing tags, they are more diverse, fine-grained, and informative. Currently, there exist several weakly-supervised hashing methods attempting to learn hash codes using tags as supervision. Although they could benefiting from the rich information contained in tags, most of them may defy the nature of social media data. In real scenarios, social media data appears in streaming fashion, but most weakly-supervised hashing methods are just batch-based which cannot effectively handle streaming data. To this end, only one weakly-supervised online hashing method has been proposed, but it is still far from enough to alleviate the negative effects of tags. In this paper, to address the above problems, we propose a new method, termed Weakly-Supervised Online Hashing with Refined Pseudo Tags (RPT-WOH). To improve the quality of weakly-supervised tags, we design the real-valued pseudo tag matrix and learn it by exploiting the correlation between the previous and new tags. Furthermore, we propose a memory-based similarity learning which could effectively maintain the semantic correlation between old and new data. In addition, we propose an effective and efficient discrete online optimization algorithm making RPT-WOH easily scalable to large-scale data. Extensive experiments conducted on two benchmark datasets demonstrate that RPT-WOH offers satisfactory performance.