Cohesion Intensive Deep Hashing for Remote Sensing Image Retrieval

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 1; p. 101
• Main Authors: Han, Lirong, Li, Peng, Bai, Xiao, Grecos, Christos, Zhang, Xiaoyu, Ren, Peng
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2020
• Subjects: Approximation; Binary codes; Codes; Cohesion; cohesion intensive; data collection; Datasets; deep hashing; Deep learning; gradualness optimization; Image management; Image retrieval; Neural networks; Optimization; Performance enhancement; Remote sensing; remote sensing image retrieval; residual net; spatial data; system optimization
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs12010101

Recently, the demand for remote sensing image retrieval is growing and attracting the interest of many researchers because of the increasing number of remote sensing images. Hashing, as a method of retrieving images, has been widely applied to remote sensing image retrieval. In order to improve hashing performance, we develop a cohesion intensive deep hashing model for remote sensing image retrieval. The underlying architecture of our deep model is motivated by the state-of-the-art residual net. Residual nets aim at avoiding gradient vanishing and gradient explosion when the net reaches a certain depth. However, different from the residual net which outputs multiple class-labels, we present a residual hash net that is terminated by a Heaviside-like function for binarizing remote sensing images. In this scenario, the representational power of the residual net architecture is exploited to establish an end-to-end deep hashing model. The residual hash net is trained subject to a weighted loss strategy that intensifies the cohesiveness of image hash codes within one class. This effectively addresses the data imbalance problem normally arising in remote sensing image retrieval tasks. Furthermore, we adopted a gradualness optimization method for obtaining optimal model parameters in order to favor accurate binary codes with little quantization error. We conduct comparative experiments on large-scale remote sensing data sets such as UCMerced and AID. The experimental results validate the hypothesis that our method improves the performance of current remote sensing image retrieval.