Multi-label multi-instance learning with missing object tags

作者：Shen, Yi^*; Peng, Jinye; Feng, Xiaoyi; Fan, Jianping

来源：Multimedia Systems, 2013, 19(1): 17-36.

DOI：10.1007/s00530-012-0290-0

• Loosely tagged images
• Distributed image clustering
• Spam tags
• Loose object tags
• Missing object tags
• Multiple instance learning
• Missing tag prediction
• Structural learning

In this paper, a novel framework is developed for leveraging large-scale loosely tagged images for object classifier training by addressing three key issues jointly: (a) spam tags e.g., some tags are more related to popular query terms rather than the image semantics; (b) loose object tags, e.g., multiple object tags are loosely given at the image level without identifying the object locations in the images; (c) missing object tags, e.g., some object tags are missed and thus negative bags may contain positive instances. To address these three issues jointly, our framework consists of the following key components for leveraging large-scale loosely tagged images for object classifier training: (1) distributed image clustering and inter-cluster visual correlation analysis for handling the issue of spam tags by filtering out large amounts of junk images automatically, (2) multiple instance learning with missing tag prediction for dealing with the issues of loose object tags and missing object tags jointly; (3) structural learning for leveraging the inter-object visual correlations to train large numbers of inter-related object classifiers jointly. Our experiments on large-scale loosely tagged images have provided very positive results.

• 出版日期2013-2
• 单位西北工业大学