Learning detectors quickly with stationary statistics

Valmadre, Jack, Sridharan, Sridha, & Lucey, Simon (2015) Learning detectors quickly with stationary statistics. In Computer Vision -- ACCV 2014: 12th Asian Conference on Computer Vision - Revised Selected Papers, Part I [ecture Notes in Computer Science, Volume 9003], Springer, Singapore, pp. 99-114.

View at publisher


Computer vision is increasingly becoming interested in the rapid estimation of object detectors. The canonical strategy of using Hard Negative Mining to train a Support Vector Machine is slow, since the large negative set must be traversed at least once per detector. Recent work has demonstrated that, with an assumption of signal stationarity, Linear Discriminant Analysis is able to learn comparable detectors without ever revisiting the negative set. Even with this insight, the time to learn a detector can still be on the order of minutes. Correlation filters, on the other hand, can produce a detector in under a second. However, this involves the unnatural assumption that the statistics are periodic, and requires the negative set to be re-sampled per detector size. These two methods differ chie y in the structure which they impose on the co- variance matrix of all examples. This paper is a comparative study which develops techniques (i) to assume periodic statistics without needing to revisit the negative set and (ii) to accelerate the estimation of detectors with aperiodic statistics. It is experimentally verified that periodicity is detrimental.

Impact and interest:

0 citations in Scopus
Search Google Scholar™

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

56 since deposited on 11 Nov 2014
8 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 68383
Item Type: Conference Paper
Refereed: Yes
Additional URLs:
DOI: 10.1007/978-3-319-16865-4_7
ISBN: 978-3-319-16864-7
Divisions: Current > Schools > School of Electrical Engineering & Computer Science
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: Copyright 2014 Springer Verlag
Deposited On: 11 Nov 2014 23:59
Last Modified: 08 Jul 2015 05:57

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page