Next Article in Journal
A Deep Learning Streaming Methodology for Trajectory Classification
Previous Article in Journal
Mining Topological Dependencies of Recurrent Congestion in Road Networks
Article

Toward Improving Image Retrieval via Global Saliency Weighted Feature

1
College of Computer Science and Technology, Jilin University, Changchun 130012, China
2
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
3
School of Mechanical Science and Engineering, Jilin University, Changchun 130025, China
*
Author to whom correspondence should be addressed.
Academic Editors: Gloria Bordogna and Wolfgang Kainz
ISPRS Int. J. Geo-Inf. 2021, 10(4), 249; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10040249
Received: 6 February 2021 / Revised: 4 April 2021 / Accepted: 5 April 2021 / Published: 8 April 2021
For full description of images’ semantic information, image retrieval tasks are increasingly using deep convolution features trained by neural networks. However, to form a compact feature representation, the obtained convolutional features must be further aggregated in image retrieval. The quality of aggregation affects retrieval performance. In order to obtain better image descriptors for image retrieval, we propose two modules in our method. The first module is named generalized regional maximum activation of convolutions (GR-MAC), which pays more attention to global information at multiple scales. The second module is called saliency joint weighting, which uses nonparametric saliency weighting and channel weighting to focus feature maps more on the salient region without discarding overall information. Finally, we fuse the two modules to obtain more representative image feature descriptors that not only consider the global information of the feature map but also highlight the salient region. We conducted experiments on multiple widely used retrieval data sets such as roxford5k to verify the effectiveness of our method. The experimental results prove that our method is more accurate than the state-of-the-art methods. View Full-Text
Keywords: image retrieval; saliency weighting; convolutional feature aggregation image retrieval; saliency weighting; convolutional feature aggregation
Show Figures

Figure 1

MDPI and ACS Style

Zhao, H.; Wu, J.; Zhang, D.; Liu, P. Toward Improving Image Retrieval via Global Saliency Weighted Feature. ISPRS Int. J. Geo-Inf. 2021, 10, 249. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10040249

AMA Style

Zhao H, Wu J, Zhang D, Liu P. Toward Improving Image Retrieval via Global Saliency Weighted Feature. ISPRS International Journal of Geo-Information. 2021; 10(4):249. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10040249

Chicago/Turabian Style

Zhao, Hongwei; Wu, Jiaxin; Zhang, Danyang; Liu, Pingping. 2021. "Toward Improving Image Retrieval via Global Saliency Weighted Feature" ISPRS Int. J. Geo-Inf. 10, no. 4: 249. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10040249

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop