Thumbnail
Access Restriction
Subscribed

Author Tao Zeng ♦ Shuiwang Ji
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©2015
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Computer programming, programs & data
Subject Keyword Brain models ♦ Gene expression ♦ Data models ♦ Biological system modeling ♦ Standards ♦ bioinformatics ♦ Deep learning ♦ multi-instance learning ♦ multi-task learning ♦ transfer learning
Abstract Multi-instance learning studies problems in which labels are assigned to bags that contain multiple instances. In these settings, the relations between instances and labels are usually ambiguous. In contrast, multi-task learning focuses on the output space in which an input sample is associated with multiple labels. In real world, a sample may be associated with multiple labels that are derived from observing multiple aspects of the problem. Thus many real world applications are naturally formulated as multi-instance multi-task (MIMT) problems. A common approach to MIMT is to solve it task-by-task independently under the multi-instance learning framework. On the other hand, convolutional neural networks (CNN) have demonstrated promising performance in single-instance single-label image classification tasks. However, how CNN deals with multi-instance multi-label tasks still remains an open problem. This is mainly due to the complex multiple-to-multiple relations between the input and output space. In this work, we propose a deep leaning model, known as multi-instance multi-task convolutional neural networks (MIMT-CNN), where a number of images representing a multi-task problem is taken as the inputs. Then a shared sub-CNN is connected with each input image to form instance representations. Those sub-CNN outputs are subsequently aggregated as inputs to additional convolutional layers and full connection layers to produce the ultimate multi-label predictions. This CNN model, through transfer learning from other domains, enables transfer of prior knowledge at image level learned from large single-label single-task data sets. The bag level representations in this model are hierarchically abstracted by multiple layers from instance level representations. Experimental results on mouse brain gene expression pattern annotation data show that the proposed MIMT-CNN model achieves superior performance.
Description Author affiliation: Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA (Tao Zeng; Shuiwang Ji)
ISSN 15504786
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research ♦ Reading
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2015-11-14
Publisher Place USA
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
e-ISBN 9781467395045
Size (in Bytes) 1.18 MB
Page Count 10
Starting Page 579
Ending Page 588


Source: IEEE Xplore Digital Library