Learning localized perceptual similarity metrics for interactive categorization
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Current similarity-based approaches to interactive fine grained categorization rely on learning metrics from holistic perceptual measurements of similarity between objects or images. However, making a single judgment of similarity at the object level can be a difficult or overwhelming task for the human user to perform. Secondly, a single general metric of similarity may not be able to adequately capture the minute differences that discriminate fine-grained categories. In this work, we propose a novel approach to interactive categorization that leverages multiple perceptual similarity metrics learned from localized and roughly aligned regions across images, reporting state-of-the-art results and outperforming methods that use a single nonlocalized similarity metric.
Originalsprog | Engelsk |
---|---|
Tidsskrift | Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015 |
Sider (fra-til) | 502-509 |
Antal sider | 8 |
DOI | |
Status | Udgivet - 19 feb. 2015 |
Eksternt udgivet | Ja |
Begivenhed | 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015 - Waikoloa, USA Varighed: 5 jan. 2015 → 9 jan. 2015 |
Konference
Konference | 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015 |
---|---|
Land | USA |
By | Waikoloa |
Periode | 05/01/2015 → 09/01/2015 |
Bibliografisk note
Publisher Copyright:
© 2015 IEEE.
ID: 301829777