Domain adaptation based on adjustable discriminator

Abstract

Abstract: The current domain adaptation (DA) based on adversarial learning has poor adaptability to target samples, lower prediction accuracy of the target domain is caused. For this reason, this paper proposes a domain adaptation (A-DADA) algorithm based on an adjustable discriminator. First, the distance between the classification probabilities of the two discriminators is used as the weight to apply to the target domain confrontation training loss function, aiming to reduce the number of confrontation training times for aligned target samples and increase the number of confrontation training times for unaligned target samples. Secondly, square entropy loss function is used as the minimum entropy loss function to improve the class balance. Finally, the Office-31 datasetis used to compare the algorithm with JAN and other algorithms, the experimental results show that compared with the JAN algorithm, the average accuracy of the algorithm is increased by 2.5%.

Key words: domain adaptation, adjustable discriminator, adversarial training, square entropy loss

CLC Number:

TP391.41

ZHAO Xiao-qiang, JIANG Hong-mei. Domain adaptation based on adjustable discriminator[J]. Journal of Lanzhou University of Technology, 2022, 48(1): 85-90.

References

[1] LECUN Y,BENGIO Y,HINTON G.Deep learning [J].Nature,2015,521(7553):436.
[2] YOSINSKI J,CLUNE J,BENGIO Y,et al.How transferable are features in deep neural networks [C]//Proceedings of the 27th International Conference on Neural Information Processing Systems.Cambridge:MIT Press,2014:3320-3328.
[3] PAN S J,YANG Q.A survey on transfer learning [J].IEEE Transactions on Knowledge & Data Engineering,2010,22(10):1345-1359.
[4] GEBRU T,HOFFMAN J,FEI-FEI L.Fine-grained recognition in the wild:a multi-task domain adaptation approach [C] //Proceedings of the 2017 IEEE International Conference on Computer Vision.Washington:IEEE Computer Society,2017:1358-1367.
[5] XIA Rui,ZONG Chengqing,HU Xuelei,et al.Feature ensemble plus sample selection:domain adaptation for sentiment classification [J].IEEE Intelligent Systems,2013,28(3):10-18.
[6] TZENG E,HOFFMAN J,ZHANG N,et al.Deep domain confusion:maximizing for domain invariance [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,2014:4010-4019.
[7] LONG Mingsheng,CAO Yue,WANG Jianmin,et al.Learning transferable features with deep adaptation networks [C]//Proceedings of the 32th International Conference on Machine Learning.New York:ACM,2015:97-105.
[8] LONG Mingsheng,ZHU Han,WANG Jianmin,et al.Deep transfer learning with joint adaptation networks [C]//Proceedings of the 34th International Conference on Machine Learning.New York:ACM,2017:2208-2017.
[9] GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets [C]//Proceedings of the 27th International Conference on Neural Information Processing Systems.Cambridge:MIT Press,2014:2672-2680.
[10] TZENG E,HOFFMAN J,SAENKO K,et al.Adversarial discriminative domain adaptation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,2017:2962-2971.
[11] GANIN Y,USTINOVA E,AJAKAN H,et al.Domain adversarial training of neural networks [J].The Journal of Machine Learning Research,2016,17(1):2096-2030.
[12] MIRZA M,OSINDERO S.Conditional generative adversarial nets [EB/OL].[2020-06-05].https://arxiv.org/abs/1411.1784.
[13] TZENG E,HOFFMAN J,SAENKO K,et al.Adversarial discriminative domain adaptation [C]//IEEE Conference on Computer Vision and Pattern Recognition.Honolulu,HI,USA:IEEE,2017:2962-2971.
[14] LONG Mingsheng,WANG Jianmin,DING Guiguang,et al.Transfer feature learning with joint distribution adaptation [C]//Proceedings of the 2013 IEEE International Conference on Computer Vision.Washington:IEEE Computer Society,2013:2200-2207.
[15] PAN S J,TSANG I W,KWOK J T,et al.Domain adaptation via transfer component analysis [J].IEEE Transactions on Neural Networks,2011,22(2):199-210.
[16] WANG Zeya,JING Baoyu,NI Yang,et al.Adversarial domain adaptation being aware of class relationships [C]//24th European Conference on Artificial Intelligence (ECAI 2020).Santiago de Compostela,Spain:[s.n.],2020:1-8.
[17] CICEK S,SOATTO S.Unsupervised domain adaptation via regularized conditional alignment [C]//2019 IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,2019:1415-1420.
[18] SAITO K,WATANABE K,USHIKU Y,et al.Maximum classifier discrepancy for unsupervised domain adaptation [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,2018:3723-3732.
[19] SAENKO K,KULIS B,FRITZ M,et al.Adapting visual category models to new domains [C]//Proceedings of the 11th European Conference on Computer Vision.Berlin:Springer,2010:213-226.
[20] PASZKE A,GROSS S,CHINTALA S,et al.Automatic differentiation in PyTorch [C]//31st Conference on Neural Information Processing System (NIPS 2017).Long Beach,CA,USA:[s.n.],2017:1-4.
[21] DENG J,DONG W,SOCHER R,et al.ImageNet:a large-scale hierarchical image database [C]//2009 IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,2009:248-255.
[22] WANG Mei,DENG Weihong.Deep visual domain adaptation:a survey [J].Neurocomputing,2018,312(27):135-153.
[23] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,2016:770-778.