Similarity comparisons for interactive fine-grained categorization
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Current human-in-the-loop fine-grained visual categorization systems depend on a predefined vocabulary of attributes and parts, usually determined by experts. In this work, we move away from that expert-driven and attribute-centric paradigm and present a novel interactive classification system that incorporates computer vision and perceptual similarity metrics in a unified framework. At test time, users are asked to judge relative similarity between a query image and various sets of images, these general queries do not require expert-defined terminology and are applicable to other domains and basic-level categories, enabling a flexible, efficient, and scalable system for fine-grained categorization with humans in the loop. Our system outperforms existing state-of-the-art systems for relevance feedback-based image retrieval as well as interactive classification, resulting in a reduction of up to 43% in the average number of questions needed to correctly classify an image.
Originalsprog | Engelsk |
---|---|
Tidsskrift | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
Sider (fra-til) | 859-866 |
Antal sider | 8 |
ISSN | 1063-6919 |
DOI | |
Status | Udgivet - 24 sep. 2014 |
Eksternt udgivet | Ja |
Begivenhed | 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, USA Varighed: 23 jun. 2014 → 28 jun. 2014 |
Konference
Konference | 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 |
---|---|
Land | USA |
By | Columbus |
Periode | 23/06/2014 → 28/06/2014 |
Bibliografisk note
Publisher Copyright:
© 2014 IEEE.
ID: 302044146