Skip navigation
Skip navigation

What has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection

Liu, Lingqiao; Wang, Lei

Description

In the past decade, the bag-of-feature model has established itself as the state-of-the-art method in various visual classification tasks. Despite its simplicity and high performance, it normally works as a black box and the classification rule is not transparent to users. However, to better understand the classification process, it is favorable to look into the black box to see how an image is recognized. To fill this gap, we developed a tool called Restricted Support Region Set (RSRS)...[Show more]

dc.contributor.authorLiu, Lingqiao
dc.contributor.authorWang, Lei
dc.coverage.spatialProvidence RI USA
dc.date.accessioned2015-12-10T23:33:14Z
dc.date.available2015-12-10T23:33:14Z
dc.date.createdJune 16-21 2012
dc.identifier.isbn1063-6919
dc.identifier.urihttp://hdl.handle.net/1885/69194
dc.description.abstractIn the past decade, the bag-of-feature model has established itself as the state-of-the-art method in various visual classification tasks. Despite its simplicity and high performance, it normally works as a black box and the classification rule is not transparent to users. However, to better understand the classification process, it is favorable to look into the black box to see how an image is recognized. To fill this gap, we developed a tool called Restricted Support Region Set (RSRS) Detection which can be utilized to visualize the image regions that are critical to the classification decision. More specifically, we define the Restricted Support Region Set for a given image as such a set of size-restricted and non-overlapped regions that if any one of them is removed the image will be wrongly classified. Focusing on the state-of-the-art bag-of-feature classification system, we developed an efficient RSRS detection algorithm and discussed its applications. We showed that it can be used to identify the limitation of a classifier, predict its failure mode, discover the classification rules and reveal the database bias. Moreover, as experimentally demonstrated, this tool also enables common users to efficiently tune the classifier by removing the inappropriate support regions, which can lead to a better generalization performance.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)
dc.sourceA Simple Prior-free Method for Non-Rigid Structure-from-Motion Factorization
dc.subjectKeywords: Black boxes; Classification decision; Classification process; Classification rules; Classification system; Detection algorithm; Generalization performance; Image regions; Region detection; State-of-the-art methods; Visual classification; Computer vision;
dc.titleWhat has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection
dc.typeConference paper
local.description.notesImported from ARIES
dc.date.issued2012
local.identifier.absfor060199 - Biochemistry and Cell Biology not elsewhere classified
local.identifier.ariespublicationf5625xPUB1951
local.type.statusPublished Version
local.contributor.affiliationLiu, Lingqiao, College of Engineering and Computer Science, ANU
local.contributor.affiliationWang, Lei, University of Wollongong
local.bibliographicCitation.startpage3586
local.bibliographicCitation.lastpage3593
local.identifier.doi10.1109/CVPR.2012.6248103
dc.date.updated2016-02-24T08:52:02Z
local.identifier.scopusID2-s2.0-84866641721
CollectionsANU Research Publications

Download

There are no files associated with this item.


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator