Targeted adversarial discriminative domain adaptation

Abstract. Domain adaptation is a technology enabling aided target recognition and other algorithms for environments and targets with data or labeled data that is scarce. Recent advances in unsupervised domain adaptation have demonstrated excellent performance but only when the domain shift is relatively small. We proposed targeted adversarial discriminative domain adaptation (T-ADDA), a semi-supervised domain adaptation method that extends the ADDA framework. By providing at least one labeled target image per class, used as a cue to guide the adaption, T-ADDA significantly boosts the performance of ADDA and is applicable to the challenging scenario in which the sets of targets in the source and target domains are not the same. The efficacy of T-ADDA is demonstrated by cross-domain, cross-sensor, and cross-target experiments using the common digits datasets and several aerial image datasets. Results demonstrate an average increase of 15% improvement with T-ADDA over ADDA using just a few labeled images when adapting to a small domain shift and afforded a 60% improvement when adapting to large domain shifts.

[1]  Trevor Darrell,et al.  Semi-Supervised Domain Adaptation via Minimax Entropy , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[2]  Yaroslav Bulatov,et al.  xView: Objects in Context in Overhead Imagery , 2018, ArXiv.

[3]  Genshe Chen,et al.  Wide-area motion imagery (WAMI) exploitation tools for enhanced situation awareness , 2012, 2012 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[4]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[5]  E. Blasch,et al.  Deep Learning Based Domain Adaptation with Data Fusion for Aerial Image Data Analysis , 2020, ICPR Workshops.

[6]  M. Rizki,et al.  Manifold Transfer Subspace Learning ( MTSL ) for High Dimensional Data — Applications to Handwritten Digits and Health Informatics , 2017 .

[7]  Gang Wang,et al.  Network survivability oriented Markov games (NSOMG) in wideband satellite communications , 2014, 2014 IEEE/AIAA 33rd Digital Avionics Systems Conference (DASC).

[8]  Genshe Chen,et al.  Space object classification using deep neural networks , 2018, 2018 IEEE Aerospace Conference.

[9]  Mingkui Tan,et al.  Domain-Symmetric Networks for Adversarial Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Andreas E. Savakis,et al.  Deep domain adaptation with manifold aligned label transfer , 2019, Machine Vision and Applications.

[11]  Haifeng Li,et al.  RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data , 2017, ArXiv.

[12]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

[13]  Xiaoqiang Lu,et al.  Remote Sensing Image Scene Classification: Benchmark and State of the Art , 2017, Proceedings of the IEEE.

[14]  Laurens van der Maaten,et al.  Learning a Parametric Embedding by Preserving Local Structure , 2009, AISTATS.

[15]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[16]  Gui-Song Xia,et al.  AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[18]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  On the Development of a Classification Based Automated Motion Imagery Interpretability Prediction , 2020, ICPR Workshops.

[20]  Genshe Chen,et al.  Prediction of compression-induced image interpretability degradation , 2018 .

[21]  Li Bai,et al.  Multiple source data fusion via sparse representation for robust visual tracking , 2011, 14th International Conference on Information Fusion.

[22]  Genshe Chen,et al.  Joint sparsity based heterogeneous data-level fusion for target detection and estimation , 2017, Defense + Security.

[23]  Genshe Chen,et al.  A joint manifold leaning-based framework for heterogeneous upstream data fusion , 2018, Journal of Algorithms & Computational Technology.

[24]  Tinne Tuytelaars,et al.  Unsupervised Visual Domain Adaptation Using Subspace Alignment , 2013, 2013 IEEE International Conference on Computer Vision.

[25]  Shawn D. Newsam,et al.  Bag-of-visual-words and spatial extensions for land-use classification , 2010, GIS '10.

[26]  Jiebo Luo,et al.  DOTA: A Large-Scale Dataset for Object Detection in Aerial Images , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[28]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[30]  Genshe Chen,et al.  Feasibility of an interpretability metric for LIDAR data , 2018, Defense + Security.

[31]  Pramod K. Varshney,et al.  Automatic registration of infrared and millimeter-wave images for concealed weapon detection , 1999, Defense, Security, and Sensing.