30/11/2020

Discrete Spatial Importance-Based Deep Weighted Hashing

Yang Shi, Xiushan Nie, Quan Zhou, Xiaoming Xi, Yilong Yin

Keywords:

Abstract Paper Similar Papers

Abstract: Hashing is a widely used technique for large-scale approximate nearest neighbor searching in multimedia retrieval. Recent works have proved that using deep neural networks is a promising solution for learning both feature representation and hash codes. However, most existing deep hashing methods directly learn hash codes from a convolutional neural network, ignoring the spatial importance distribution of images. The loss of spatial importance negatively affects the performance of hash learning and thus reduces its accuracy. To address this issue, we propose a new deep hashing method with weighted spatial information, which generates hash codes by using discrete spatial importance distribution. In particular, to extract the discrete spatial importance information of images effectively, we propose a method to learn the spatial attention map and hash code simultaneously, which makes the spatial attention map more conductive to hash-based retrieval. The experimental results of three widely used datasets show that the proposed deep weighted hashing method is superior to the state-of-the-art hashing method.

The video of this talk cannot be embedded. You can watch it here:
https://accv2020.github.io/miniconf/poster_659.html
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ACCV 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 18:07 
 0
 0
 0
 0
 14:20 
 0
 0
 0
 0
 13:11 
 0
 0
 0
 0
 12:22 
 0
 0
 0
 0
 3:46 
 0
 0
 0
 0
 8:31 
 0
 0
 0
 0
 2:57 
 1
 1
 0
 1
 5:09 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 11:26 
 0
 0
 0
 0
 2:55 
 0
 0
 0
 0
 8:41 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 4:34 
 0
 0
 0
 0
 9:26 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 5:05 
 0
 1
 0
 1
 3:18 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 1
 5:01 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 2:58 
 0
 0
 0
 0
 13:15 
 0
 0
 0
 0
 14:21 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 12:04 
 1
 0
 0
 0
 14:01 
 0
 0
 0
 0
 17:30 
 0
 0
 0
 0
 12:10 
 0
 0
 0
 0
 4:41 
 0
 0
 0
 0
 14:32 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 9:28 
 0
 0
 0
 0
 10:12 
 0
 0
 0
 0
 1:03 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 9:19 
 0
 0
 0
 0
 14:30