Novelty Detection Under The Multi-Instance Multi-Label Framework Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_projects/2f75rc84g

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • Novelty detection plays an important role in machine learning and signal processing. This project studies novelty detection in a new setting where the data object is represented as a bag of instances and associated with multiple class labels, referred to as multi-instance multi-label (MIML) learning. Contrary to the common assumption in MIML that each instance in a bag belongs to one of the known classes, in novelty detection, we focus on the scenario where bags may contain novel-class instances. The goal is to determine, for any given instance in a new bag, whether it belongs to a known class or a novel class. Detecting novelty in the MIML setting captures many real-world phenomena and has many potential applications. For example, in a collection of tagged images, the tag may only cover a subset of objects existing in the images. Discovering an object whose class has not been previously tagged can be useful for the purpose of soliciting a label for the new object class. To address this novel problem, we present a discriminative framework for detecting new class instances. Experiments demonstrate the effectiveness of our proposed method, and reveal that the presence of unlabeled novel instances in training bags is helpful to the detection of such instances in testing stage. To the best of our knowledge, novelty detection in the MIML setting has not been investigated. Our main contributions are: (i) We propose a new problem – novelty detection in the MIML setting. (ii) We offer a framework based on score functions to solve the problem. (iii) We illustrate the efficacy of our method on a real-world MIML bioacoustics data.
Resource Type
Date Available
Date Copyright
Date Issued
Advisor
Committee Member
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Made available in DSpace on 2014-01-14T23:51:16Z (GMT). No. of bitstreams: 1 MS_Qi_Lou.pdf: 708524 bytes, checksum: 5bcb8f3180f6e85dec88e6c43bde40a3 (MD5) Previous issue date: 2013-11-26
  • description.provenance : Approved for entry into archive by Sue Kunda(sue.kunda@oregonstate.edu) on 2014-01-14T23:51:16Z (GMT) No. of bitstreams: 1 MS_Qi_Lou.pdf: 708524 bytes, checksum: 5bcb8f3180f6e85dec88e6c43bde40a3 (MD5)
  • description.provenance : Approved for entry into archive by Sue Kunda(sue.kunda@oregonstate.edu) on 2014-01-14T23:47:42Z (GMT) No. of bitstreams: 1 MS_Qi_Lou.pdf: 708524 bytes, checksum: 5bcb8f3180f6e85dec88e6c43bde40a3 (MD5)
  • description.provenance : Submitted by Qi Lou (louq@onid.orst.edu) on 2014-01-14T22:13:44Z No. of bitstreams: 1 MS_Qi_Lou.pdf: 708524 bytes, checksum: 5bcb8f3180f6e85dec88e6c43bde40a3 (MD5)

Relationships

In Administrative Set:
Last modified: 10/05/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items