Supervised Feature Quantization with Entropy Optimization
(2011) 1st IEEE Workshop on Information Theory in Computer Vision and Pattern Recognition (ICCV 2011), 2011 p.1386-1393- Abstract
- Feature quantization is a crucial component for efficient large scale image retrieval and object recognition. By quantizing local features into visual words, one hopes that features that match each other obtain the same word ID. Then, similarities between images can be measured with respect to the corresponding histograms of visual words. Given the appearance variations of local features, traditional quantization methods do not take into account the distribution of matched features. In this paper, we investigate how to encode additional prior information on the feature distribution via entropy optimization by leveraging ground truth correspondence data. We propose a computationally efficient optimization scheme for large scale vocabulary... (More)
- Feature quantization is a crucial component for efficient large scale image retrieval and object recognition. By quantizing local features into visual words, one hopes that features that match each other obtain the same word ID. Then, similarities between images can be measured with respect to the corresponding histograms of visual words. Given the appearance variations of local features, traditional quantization methods do not take into account the distribution of matched features. In this paper, we investigate how to encode additional prior information on the feature distribution via entropy optimization by leveraging ground truth correspondence data. We propose a computationally efficient optimization scheme for large scale vocabulary training. The results from our experiments suggest that entropy-optimized vocabulary performs better than unsupervised quantization methods in terms of recall and precision for feature matching. We also demonstrate the advantage of the optimized vocabulary for image retrieval. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/2214469
- author
- Kuang, Yubin LU ; Byröd, Martin LU and Åström, Karl LU
- organization
- publishing date
- 2011
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- visual vocabulary, entropy optimization
- host publication
- Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on
- pages
- 8 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 1st IEEE Workshop on Information Theory in Computer Vision and Pattern Recognition (ICCV 2011), 2011
- conference location
- Barcelona, Spain
- conference dates
- 2011-11-06 - 2011-11-13
- external identifiers
-
- wos:000300056700199
- scopus:84856683513
- ISBN
- 978-1-4673-0062-9 (print)
- DOI
- 10.1109/ICCVW.2011.6130413
- language
- English
- LU publication?
- yes
- id
- 9f1f70f9-27fd-40fe-9da6-8520edf4434d (old id 2214469)
- date added to LUP
- 2016-04-04 11:42:47
- date last changed
- 2022-01-29 22:20:19
@inproceedings{9f1f70f9-27fd-40fe-9da6-8520edf4434d, abstract = {{Feature quantization is a crucial component for efficient large scale image retrieval and object recognition. By quantizing local features into visual words, one hopes that features that match each other obtain the same word ID. Then, similarities between images can be measured with respect to the corresponding histograms of visual words. Given the appearance variations of local features, traditional quantization methods do not take into account the distribution of matched features. In this paper, we investigate how to encode additional prior information on the feature distribution via entropy optimization by leveraging ground truth correspondence data. We propose a computationally efficient optimization scheme for large scale vocabulary training. The results from our experiments suggest that entropy-optimized vocabulary performs better than unsupervised quantization methods in terms of recall and precision for feature matching. We also demonstrate the advantage of the optimized vocabulary for image retrieval.}}, author = {{Kuang, Yubin and Byröd, Martin and Åström, Karl}}, booktitle = {{Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on}}, isbn = {{978-1-4673-0062-9 (print)}}, keywords = {{visual vocabulary; entropy optimization}}, language = {{eng}}, pages = {{1386--1393}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Supervised Feature Quantization with Entropy Optimization}}, url = {{http://dx.doi.org/10.1109/ICCVW.2011.6130413}}, doi = {{10.1109/ICCVW.2011.6130413}}, year = {{2011}}, }