| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Unsupervised Object Discovery for Instance Recognition
Abstract : Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discrim-inative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The descriptors derived from the salient regions improve particular object retrieval, most noticeably in a large collections containing small objects.
Cited literature [46 references]
https://hal.inria.fr/hal-01842143
Contributor : Yannis Avrithis <>
Submitted on : Wednesday, July 18, 2018 - 12:46:58 AM
Last modification on : Friday, July 10, 2020 - 4:01:28 PM
Long-term archiving on: : Friday, October 19, 2018 - 4:07:43 PM
Contributor : Yannis Avrithis <>
Submitted on : Wednesday, July 18, 2018 - 12:46:58 AM
Last modification on : Friday, July 10, 2020 - 4:01:28 PM
Long-term archiving on: : Friday, October 19, 2018 - 4:07:43 PM
File
C105.wacv18.disco.pdf
Files produced by the author(s)