What has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection
-
Altmetric Citations
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.author | Liu, Lingqiao | |
---|---|---|
dc.contributor.author | Wang, Lei | |
dc.coverage.spatial | Providence RI USA | |
dc.date.accessioned | 2015-12-10T23:33:14Z | |
dc.date.available | 2015-12-10T23:33:14Z | |
dc.date.created | June 16-21 2012 | |
dc.identifier.isbn | 1063-6919 | |
dc.identifier.uri | http://hdl.handle.net/1885/69194 | |
dc.description.abstract | 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) 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.publisher | Institute of Electrical and Electronics Engineers (IEEE Inc) | |
dc.relation.ispartofseries | IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012) | |
dc.source | A Simple Prior-free Method for Non-Rigid Structure-from-Motion Factorization | |
dc.subject | Keywords: 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.title | What has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection | |
dc.type | Conference paper | |
local.description.notes | Imported from ARIES | |
dc.date.issued | 2012 | |
local.identifier.absfor | 060199 - Biochemistry and Cell Biology not elsewhere classified | |
local.identifier.ariespublication | f5625xPUB1951 | |
local.type.status | Published Version | |
local.contributor.affiliation | Liu, Lingqiao, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Wang, Lei, University of Wollongong | |
local.bibliographicCitation.startpage | 3586 | |
local.bibliographicCitation.lastpage | 3593 | |
local.identifier.doi | 10.1109/CVPR.2012.6248103 | |
dc.date.updated | 2016-02-24T08:52:02Z | |
local.identifier.scopusID | 2-s2.0-84866641721 | |
Collections | ANU Research Publications |
Download
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator