Deep Feature Factorization for Concept Discovery

We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we detect hierarchical cluster structures in feature space. This is visualized as heat maps, which highlight semantically matching regions across a set of images, revealing what the network 'perceives' as similar. DFF can also be used to perform co-segmentation and co-localization, and we report state-of-the-art results on these tasks.


Published in:
Proceedings of the 15th European Conference on Computer Vision, 14, 352-368
Presented at:
15th European Conference on Computer Vision (ECCV), Munich, Germany, September 8-11, 2018
Year:
2018
Publisher:
SpringerLink
ISBN:
978-3-030-01267-0
Keywords:
Laboratories:




 Record created 2019-01-10, last modified 2019-06-19

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)