Semantic matching by weakly supervised 2D point set registration

Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)

Authors

Date

2019-03-04

Department

Department of Computer Science

Major/Subject

Mcode

Degree programme

Language

en

Pages

9

Series

2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), pp. 1061-1069

Abstract

In this paper we address the problem of establishing correspondences between different instances of the same object. The problem is posed as finding the geometric transformation that aligns a given image pair. We use a convolutional neural network (CNN) to directly regress the parameters of the transformation model. The alignment problem is defined in the setting where an unordered set of semantic key-points per image are available, but, without the correspondence information. To this end we propose a novel loss function based on cyclic consistency that solves this 2D point set registration problem by inferring the optimal geometric transformation model parameters. We train and test our approach on a standard benchmark dataset Proposal-Flow (PF-PASCAL)[8]. The proposed approach achieves state-of-the-art results demonstrating the effectiveness of the method. In addition, we show our approach further benefits from additional training samples in PF-PASCAL generated by using category level information.

Description

Keywords

Other note

DOI

10.1109/WACV.2019.00118

Citation

Laskar, Z, Tavakoli, H R & Kannala, J 2019, Semantic matching by weakly supervised 2D point set registration . in 2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) ., 8658796, IEEE, pp. 1061-1069, IEEE Winter Conference on Applications of Computer Vision, Waikoloa Village, Hawaii, United States, 07/01/2019 . https://doi.org/10.1109/WACV.2019.00118

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-201907304541

Collections

[article-cris] Perustieteiden korkeakoulu / SCI