Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback
-
Altmetric Citations
Joshi, Ajay J.; Porikli, Fatih; Papanikolopoulos, Nikolaos
Description
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated - providing this can be impractical for the user when a large (and possibly unknown) number of categories are present. In this paper, we propose a multi-class active learning model that requires only binary (yes/no type) feedback from the user. For instance, given two images the user only has to say whether they belong to the same class or not. We...[Show more]
Collections | ANU Research Publications |
---|---|
Date published: | 2010 |
Type: | Conference paper |
URI: | http://hdl.handle.net/1885/31045 |
Source: | Proceedings of The 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010) |
DOI: | 10.1109/CVPR.2010.5540047 |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Joshi_Breaking_the_interactive_2010.pdf | 774.85 kB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator