[1]FEI Yujie,WU Xiaojun.A new feature coding algorithm based on the combination of group salient coding and VLAD[J].CAAI Transactions on Intelligent Systems,2017,12(2):172-178.[doi:10.11992/tis.201602010]
Copy
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
12
Number of periods:
2017 2
Page number:
172-178
Column:
学术论文—机器学习
Public date:
2017-05-05
- Title:
-
A new feature coding algorithm based on the combination of group salient coding and VLAD
- Author(s):
-
FEI Yujie; WU Xiaojun
-
School of IoT Engineering, Jiangnan University, Wuxi 214122, China
-
- Keywords:
-
image classification; feature coding; bag-of-features; VLAD; soft assignment; saliency
- CLC:
-
TP391
- DOI:
-
10.11992/tis.201602010
- Abstract:
-
The vector of locally aggregated descriptors (VLAD) has achieved good results in addressing large-scale image retrieval problems; however, VLAD has a defect in that the relationship between local descriptors and visual words cannot be accurately described using hard assignments. In this paper, we therefore combine two kinds of soft assignment coding methods with VLAD to enhance the relationship between local feature vectors and visual words. We applied our method to 15 scenes from the Corel 10 and UIUC Sports Event datasets, with our experimental results showing that our combined partial soft assignment coding method and VLAD was able to enhance classification accuracy and achieve better classification accuracy than the well-known Fisher Coding approach. In addition to soft assignment, saliency also plays an important role in enhancing classification accuracy.