AAAI Publications, Thirty-First AAAI Conference on Artificial Intelligence

Font Size: 
Deep MIML Network
Ji Feng, Zhi-Hua Zhou

Last modified: 2017-02-13

Abstract


In many real world applications, the concerned objects are with multiple labels, and can be represented as a bag of instances. Multi-instance Multi-label (MIML) learning provides a framework for handling such task and has exhibited excellent performance in various domains. In a MIML setting, the feature representation of instances usually has big impact on the final performance; inspired by the recent deep learning studies, in this paper, we propose the DeepMIML network which exploits deep neural network formation to generate instance representation for MIML. The sub-concept learning component of the DeepMIML structure reserves the instance-label relation discovery ability of MIML algorithms; that is, it can automatically locating the key input patterns that trigger the labels. The effectiveness of DeepMIML network is validated by experiments on various domains of data.

Keywords


deep learning;multi-instance multi-label learning

Full Text: PDF