This paper introduces a simple but effective way to boost the performance of scene classification through a novel approach to the LLC coding process. In our proposed method, a local descriptor is encoded not only with k-nearest visual words but also with k-farthest visual words to produce more discriminative code. Since the proposed method is a simple modification of the image classification model, it can be easily integrated into various existing BoF models proposed in various areas, such as coding, pooling, to boost their scene classification performance. The results of experiments conducted with three scene datasets: 15-Scenes, MIT-Indoor67, and Sun367 show that adding k-farthest visual words better enhances scene classification performance than increasing the number of k-nearest visual words.
Katsuyuki TANAKA
Kobe University
Tetsuya TAKIGUCHI
Kobe University
Yasuo ARIKI
Kobe University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Katsuyuki TANAKA, Tetsuya TAKIGUCHI, Yasuo ARIKI, "LLC Revisit: Scene Classification with k-Farthest Neighbours" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 5, pp. 1375-1383, May 2016, doi: 10.1587/transinf.2015EDP7332.
Abstract: This paper introduces a simple but effective way to boost the performance of scene classification through a novel approach to the LLC coding process. In our proposed method, a local descriptor is encoded not only with k-nearest visual words but also with k-farthest visual words to produce more discriminative code. Since the proposed method is a simple modification of the image classification model, it can be easily integrated into various existing BoF models proposed in various areas, such as coding, pooling, to boost their scene classification performance. The results of experiments conducted with three scene datasets: 15-Scenes, MIT-Indoor67, and Sun367 show that adding k-farthest visual words better enhances scene classification performance than increasing the number of k-nearest visual words.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7332/_p
Copy
@ARTICLE{e99-d_5_1375,
author={Katsuyuki TANAKA, Tetsuya TAKIGUCHI, Yasuo ARIKI, },
journal={IEICE TRANSACTIONS on Information},
title={LLC Revisit: Scene Classification with k-Farthest Neighbours},
year={2016},
volume={E99-D},
number={5},
pages={1375-1383},
abstract={This paper introduces a simple but effective way to boost the performance of scene classification through a novel approach to the LLC coding process. In our proposed method, a local descriptor is encoded not only with k-nearest visual words but also with k-farthest visual words to produce more discriminative code. Since the proposed method is a simple modification of the image classification model, it can be easily integrated into various existing BoF models proposed in various areas, such as coding, pooling, to boost their scene classification performance. The results of experiments conducted with three scene datasets: 15-Scenes, MIT-Indoor67, and Sun367 show that adding k-farthest visual words better enhances scene classification performance than increasing the number of k-nearest visual words.},
keywords={},
doi={10.1587/transinf.2015EDP7332},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - LLC Revisit: Scene Classification with k-Farthest Neighbours
T2 - IEICE TRANSACTIONS on Information
SP - 1375
EP - 1383
AU - Katsuyuki TANAKA
AU - Tetsuya TAKIGUCHI
AU - Yasuo ARIKI
PY - 2016
DO - 10.1587/transinf.2015EDP7332
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2016
AB - This paper introduces a simple but effective way to boost the performance of scene classification through a novel approach to the LLC coding process. In our proposed method, a local descriptor is encoded not only with k-nearest visual words but also with k-farthest visual words to produce more discriminative code. Since the proposed method is a simple modification of the image classification model, it can be easily integrated into various existing BoF models proposed in various areas, such as coding, pooling, to boost their scene classification performance. The results of experiments conducted with three scene datasets: 15-Scenes, MIT-Indoor67, and Sun367 show that adding k-farthest visual words better enhances scene classification performance than increasing the number of k-nearest visual words.
ER -