Domain Adaptive Algorithm for Minimizing Class Confusion Combined with Style Transfer

doi:10.3778/j.issn.1002-8331.2101-0042

Abstract

Abstract: In unsupervised domain adaptation, a classifier is easily to produce the confusion prediction when it predicts the class of samples of a target domain, though existing studies have proposed that the class correlation of samples is extracted by relevant algorithms which reduce a classifier’s confusion prediction in the target domain, this method remains problems unsolved that the transfer learning ability is inadequate in a source domain and target domain because of sparse shared features, targeted to which, through application of generative adversarial nets to migrate the style of a source domain, to extend shared features of various samples of feature space in source domain available for source domain matching to solve the problem of classifier’s insufficient positive transfer ability led by sparse shared features, thus to further reduce a classifier’s class confusion prediction produced in a target domain. When a classifier predicts the classified probability of samples of a target domain by using extended shared features, based on uncertainty of weighting system to add the weighting of predictive probability to make it be highlighted with higher probability values on several predicted probability peaks for an accurate quantitative class confusion, it minimizes cross-origin class confusion prediction and inhibits cross-origin negative transfer. Under UDA scene, domain adaptive experiments have been conducted respectively for three sub-data sets of standard data set ImageCLEF-DA and Office-31, and whose average recognition precision are higher by 1.3 percentage points and 1.7 percentage points respectively compared with RADA algorithm.

Key words: transfer learning, minimizing class confusion, style transfer, domain adaptation, generative adversarial network

摘要： 在无监督领域自适应中分类器对目标域的样本进行类别预测时容易产生混淆预测，虽然已有研究提出了相关算法提取到样本的类间相关性，降低了分类器在目标域上的类混淆预测。但该方法仍然未能解决源域和目标域因共享特征稀疏导致的迁移学习能力不足的问题，针对这个问题，通过使用生成对抗网络对源域进行了风格迁移，扩展源域各类样本的特征空间可供目标域匹配的共享特征，解决因共享特征稀疏导致分类器正迁移力不足的问题，从而进一步减少分类器在目标域上产生的类混淆预测。当分类器利用扩充后的共享特征对目标域样本预测分类概率时，基于不确定性权重机制，加重预测概率权重使其能在几个预测概率峰值上以更高的概率值突出，准确地量化类混淆，最小化跨域的类混淆预测，抑制跨域的负迁移。在UDA场景下，对标准的数据集ImageCLEF-DA和Office-31的三个子数据集分别进行了领域自适应实验，相较于RADA算法平均识别精度分别提升了1.3个百分点和1.7个百分点。

关键词: 迁移学习, 最小化类混淆, 风格迁移, 领域自适应, 生成对抗网络

MEI Xiaojie, ZHANG Ling. Domain Adaptive Algorithm for Minimizing Class Confusion Combined with Style Transfer[J]. Computer Engineering and Applications, 2022, 58(14): 153-159.

梅校杰, 张灵. 结合风格迁移的最小化类混淆领域自适应算法[J]. 计算机工程与应用, 2022, 58(14): 153-159.

References

[1] QUIONEROCANDELA J，SUGIYAMA M，SCHWAIGHOFER A，et al.Dataset shift in machine learning[M]//London，England：The MIT Press，2009：27-52.
[2] PAN S J，YANG Q.A survey on transfer learning[J].IEEE Transactions on Knowledge and Data Engineering，2010，22（10）：1345-1359.
[3] WANG X M，LI L，YE W R，et al.Transferable attention for domain adaptation[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：422-433.
[4] ZHANG Y C，LIU T L，LONG M S，et al.Bridging theory and algorithm for domain adaptation[J].arXiv：1904.05801，2019.
[5] SUN B，SAENKO K.Deep coral：correlation alignment for deep domain adaptation[C]//European Conference on Computer Vision，2016：443-450.
[6] TZENG E，HOFFMAN J，ZHANG N，et al.Deep domain confusion：maximizing for domain invariance[J].arXiv：1412.3474，2014.
[7] LONG M S，CAO Y，WANG J M，et al.Learning transferable features with deep adaptation networks[C]//Proceedings of the International Conference on Machine Learning（ICML），2015：97-105.
[8] LONG M S，ZHU H，WANG J M，et al.Deep transfer learning with joint adaptation networks[C]//34th International Conference on Machine Learning，2017：2208-2217.
[9] LEE C Y，BATRA T，BAIG M H，et al.Sliced wasserstein discrepancy for unsupervised domain adaptation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2019：10277-10287.
[10] ZHANG W C，OUYANG W L，LI W，et al.Collaborative and adversarial network for unsupervised domain adaptation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：3801-3809.
[11] GANIN Y，USTINOVA E，AJAKAN H，et al.Domain adversarial training of neural networks[J].Journal of Machine Learning Research，2016，17（1）：2096-2030.
[12] PEI Z Y，CAO Z J，LONG M S，et al.Multi-adversarial domain adaptation[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2018：3934-3941.
[13] WANG Z Y，JING B Y，NI Y，et al.Adversarial domain adaptation being aware of class relationships[J].arXiv：1905.11931，2019.
[14] JIN Y，WANG X M，LONG M S，et al.Minimum class confusion for versatile domain adaptation[C]//European Conference on Computer Vision，2020：464-480.
[15] ZHU J Y，PARK T，ISOLA P，et al.Unpaired image-to-image translation using cycle consistent adversarial networks[C]//Proc of IEEE International Conference on Computer Vision，2017：2223-2232.
[16] BOUSMALIS K，SILBERMAN N，DOHAN D，et al.Unsupervised pixel-level domain adaptation with generative adversarial networks[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017：95-104.
[17] HOFFMAN J，TZENG E，PARK T，et al.Cycle consistent adversarial domain adaptation[C]//Proceedings of the International Conference on Machine Learning，2018：1989-1998.
[18] 王通平，傅可人，程鹏.基于图像风格迁移的人脸识别域适应方法[J].计算机应用研究，2020，37（11）：3496-3499.
WANG T P，FU K R，CHENG P.Domain adaption for face recognition based on image style transfer[J].Application Research of Computers，2020，37（11）：3496-3499.
[19] XU R J，CHEN Z L，ZUO W M，et al.Deep cocktail network：multi-source unsupervised domain adaptation with category shift[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：3964-3973.
[20] GUO C，PLEISS G，SUN Y，et al.On calibration of modern neural networks[C]//Proceedings of the International Conference on Machine Learning，2017：1321-1330.
[21] HINTON G，VINYALS O，DEAN J.Distilling the knowledge in a neural network[J].arXiv：1503.02531，2015.
[22] SCHUTZE H，MANNING C D，RAGHAVAN P.Introduction to information retrieval[C]//Proceedings of the International Communication of Association for Computing machinery Conference，2008：219-289.
[23] LUXBURG U.A tutorial on spectral clustering[J].Statistics and Computing，2007，17（4）：395-416.
[24] SAENKO K，KULIS B，FRITZ M，et al.Adapting visual category models to new domains[C]//European Conference on Computer Vision，2010：213-226.
[25] LONG M S，ZHU H，WANG J M，et al.Unsupervised domain adaptation with residual transfer networks[C]//Conference and Workshop on Neural Information Processing Systems，2016：136-144.
[26] TZENG E，HOFFMAN J，SAENKO K，et al.Adversarial discriminative domain adaptation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017：2962-2971.
[27] CHEN C，CHEN Z H，JIANG B Y，et al.Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：3296-3303.
[28] 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.
[29] GONG B Q，SHI Y，SHA F，et al.Geodesic flow kernel for unsupervised domain adaptation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2012：2066-2073.
[30] MAATEN L，HINTON G.Visualizing data using t-SNE[J].Journal of Machine Learning Research，2008，9：2579-2605.