Deep Adversarial Domain Adaptation Method for Cross-Domain Classification in High-Resolution Remote Sensing Images

Wenxiu Teng; Ni Wang; Taisheng Chen; Benlin Wang; Menglin Chen; Huihui Shi

doi:10.3788/LOP56.112801

Laser & Optoelectronics Progress, Volume. 56, Issue 11, 112801(2019)

Deep Adversarial Domain Adaptation Method for Cross-Domain Classification in High-Resolution Remote Sensing Images

Wenxiu Teng^1、**, Ni Wang^2,3、*, Taisheng Chen^2,3, Benlin Wang^2,3,4, Menglin Chen^2,3, and Huihui Shi³

Author Affiliations

¹ College of Forest, Nanjing Forestry University, Nanjing, Jiangsu 210037, China

² School of Geographic Information and Tourism, Chuzhou University, Chuzhou, Anhui 239000, China

³ Anhui Engineering Laboratory of Geographical Information Intelligent Sensor and Service, Chuzhou, Anhui 239000, China

⁴ School of Earth Sciences and Engineering, Hohai University, Nanjing, Jiangsu 210098, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(9)

Fig. 1. Framework of proposed method. (a) High spatial resolution remote sensing image dataset; (b) source deep convolutional neural network; (c) unsupervised adversarial domain adaptation; (d) remote sensing image scene classification

Download full size

Fig. 2. Sample images of UC-Merced dataset

Download full size

Fig. 3. Sample images of WHU-RS dataset

Download full size

Fig. 4. Classification confusion matrix of UC-Merced dataset. (a) Classification accuracy of source domain; (b) classification accuracy of domain adaptation

Download full size

Fig. 5. Classification confusion matrix of WHU-RS dataset. (a) Classification accuracy of source only; (b) classification accuracy of domain adaptation

Download full size

Table 1. Dataset category for remote sensing image scene classification of source domain

View table

Table 1. Dataset category for remote sensing image scene classification of source domain

Large class(six)	Subclass(seventy-one)
Construction land	city_building, container, storage_room, pipeline, town, baseball_diamond, basketball_court, golf_course, tennis_court, ground_track_field, church, commercial_area, industrial_area, mobile_home_park, palace, stadium, thermal_power_station, dense_ residential, medium_residential, sparse_residential, Square, Center, Park, Resort, School, Playground
Ultivated land	green_farmland, dry_farm, bare_land, circular_farmland, rectangular_ farmland, terrace
Transportation	airplane, airport_runway, avenue, highway, harbor, parkinglot, crossroads, bridge, airport, overpass, railway, railway_station, ship, roundabout
Water area	beach, dam, hirst, lakeshore, river, sea, stream, island, lake, sea_ice, wetland
Woodland	artificial_grassland, sparse_forest, forest, mangrove, sapling, river_protection_forest, shrubwood, chaparral, meadow
Other	desert, snow_mountain, mountain, sandbeach, cloud

Table 2. Deep convolution neural network structure of source domain and target domain

View table

Table 2. Deep convolution neural network structure of source domain and target domain

Layer name	Layer type	Output size /(pixel×pixel×pixel)
Source /targetDCNN	Input	224×224×3
	Convolution×2	224×224×64
	Map pooling	112×112×64
	Convolution×2	112×112×128
	Map pooling	56×56×128
	Convolution×3	56×56×256
	Map pooling	28×28×256
	Convolution×3	28×28×512
	Map pooling	14×14×512
	Convolution×3	14×14×512
	Map pooling	7×7×512
	Fully connected	1×1×1024
	Softmax	1×1×18/1×1×21

Table 3. Structure of discriminator
View table
Table 3. Structure of discriminator
Layer name Layer type Output size /(pixel×pixel×pixel)
Discriminator Fully connected 1×1×1024
Fully connected 1×1×512
Fully connected 1×1×2
Softmax 1×1×2

Table 4. Classification accuracy of each algorithm%
View table
Table 4. Classification accuracy of each algorithm%
Algorithm Source only MMD DANN Proposed
UC-Merced 70.43 82.19 81.62 86.71
WHU-RS 87.06 94.83 93.83 97.41

Tools

Get Citation

Copy Citation Text

Wenxiu Teng, Ni Wang, Taisheng Chen, Benlin Wang, Menglin Chen, Huihui Shi. Deep Adversarial Domain Adaptation Method for Cross-Domain Classification in High-Resolution Remote Sensing Images[J]. Laser & Optoelectronics Progress, 2019, 56(11): 112801

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Remote Sensing and Sensors

Received: Dec. 17, 2018

Accepted: Dec. 25, 2018

Published Online: Jun. 13, 2019

The Author Email: Wenxiu Teng (wenxiu_teng@163.com), Ni Wang (wnstrive@163.com)

DOI:10.3788/LOP56.112801

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Dataset category for remote sensing image scene classification of source domain

Table 1. Dataset category for remote sensing image scene classification of source domain

Table 2. Deep convolution neural network structure of source domain and target domain

Table 2. Deep convolution neural network structure of source domain and target domain

Table 3. Structure of discriminator

Table 3. Structure of discriminator

Table 4. Classification accuracy of each algorithm%

Table 4. Classification accuracy of each algorithm%