Improving Domain Adaptation by Source Selection

Domain adaptation consists in learning from a source data distribution a model that will be used on a different target data distribution. The domain adaptation procedure is usually unsuccessful if the source domain is too different from the target one. In this paper, we study domain adaptation for image classification with deep learning in the context of multiple available source domains. We propose a multisource domain adaptation method that selects and weights the sources based on inter-domain distances. We provide encouraging results on both classical benchmarks and a new real world application with 21 domains.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  Arun Ross,et al.  On automated source selection for transfer learning in convolutional neural networks , 2018, Pattern Recognit..

[3]  Thomas G. Dietterich,et al.  To transfer or not to transfer , 2005, NIPS 2005.

[4]  Ye Xu,et al.  Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias , 2013, 2013 IEEE International Conference on Computer Vision.

[5]  Jing Gao,et al.  On handling negative transfer and imbalanced distributions in multiple source transfer learning , 2014, SDM.

[6]  Koby Crammer,et al.  A theory of learning from different domains , 2010, Machine Learning.

[7]  Alexei A. Efros,et al.  Undoing the Damage of Dataset Bias , 2012, ECCV.

[8]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[10]  Dong Xu,et al.  Exploiting web images for event recognition in consumer videos: A multiple source domain adaptation approach , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Marco Loog,et al.  Distance Based Source Domain Selection for Sentiment Classification , 2018, ArXiv.

[13]  Jianmin Wang,et al.  Partial Transfer Learning with Selective Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Rémi Emonet,et al.  Improving Chairlift Security with Deep Learning , 2017, IDA.

[15]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[16]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

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