University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Geometric Mining: Scaling Geometric Hashing to Large Datasets

Gilbert, Andrew and Bowden, Richard (2015) Geometric Mining: Scaling Geometric Hashing to Large Datasets In: 3rd Workshop on Web-scale Vision and Social Media (VSM), at ICCV 2015, 18 December 2015, Santiago, Chile.

[img]
Preview
Text
egpaper_for_review.pdf
Available under License : See the attached licence file.

Download (8MB) | Preview
[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

It is known that relative feature location is important in representing objects, but assumptions that make learning tractable often simplify how structure is encoded e.g. spatial pooling or star models. For example, techniques such as spatial pyramid matching (SPM), in-conjunction with machine learning techniques perform well [13]. However, there are limitations to such spatial encoding schemes which discard important information about the layout of features. In contrast, we propose to use the object itself to choose the basis of the features in an object centric approach. In doing so we return to the early work of geometric hashing [18] but demonstrate how such approaches can be scaled-up to modern day object detection challenges in terms of both the number of examples and their variability. We apply a two stage process; initially filtering background features to localise the objects and then hashing the remaining pairwise features in an affine invariant model. During learning, we identify class-wise key feature predictors. We validate our detection and classification of objects on the PASCAL VOC’07 and ’11 [6] and CarDb [21] datasets and compare with state of the art detectors and classifiers. Importantly we demonstrate how structure in features can be efficiently identified and how its inclusion can increase performance. This feature centric learning technique allows us to localise objects even without object annotation during training and the resultant segmentation provides accurate state of the art object localization, without the need for annotations.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
AuthorsEmailORCID
Gilbert, AndrewUNSPECIFIEDUNSPECIFIED
Bowden, RichardUNSPECIFIEDUNSPECIFIED
Date : 18 December 2015
Additional Information : This is the Open Access version, provided by the Computer Vision Foundation. Copyright is retained by the authors
Depositing User : Symplectic Elements
Date Deposited : 19 Jan 2016 10:23
Last Modified : 19 Jan 2016 10:25
URI: http://epubs.surrey.ac.uk/id/eprint/809494

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800