Identifying Analogies Across Domains

Identifying analogies across domains without supervision is an important task for artificial intelligence. Recent advances in cross domain image mapping have concentrated on translating images across domains. Although the progress made is impressive, the visual fidelity many times does not suffice for identifying the matching sample from the other domain. In this paper, we tackle this very task of finding exact analogies between datasets i.e. for every image from domain A find an analogous image in domain B. We present a matching-by-synthesis approach: AN-GAN, and show that it outperforms current techniques. We further show that the cross-domain mapping task can be broken into two parts: domain alignment and learning the mapping function. The tasks can be iteratively solved, and as the alignment is improved, the unsupervised translation function reaches quality comparable to full supervision.

[1]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[2]  Hyunsoo Kim,et al.  Learning to Discover Cross-Domain Relations with Generative Adversarial Networks , 2017, ICML.

[3]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[4]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[5]  Lior Wolf,et al.  Unsupervised Cross-Domain Image Generation , 2016, ICLR.

[6]  Lior Wolf,et al.  One-Sided Unsupervised Domain Mapping , 2017, NIPS.

[7]  Tie-Yan Liu,et al.  Dual Learning for Machine Translation , 2016, NIPS.

[8]  Kristen Grauman,et al.  Fine-Grained Visual Comparisons with Local Learning , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Jayakorn Vongkulbhisal,et al.  Discriminative Optimization: Theory and Applications to Computer Vision , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Vladlen Koltun,et al.  Photographic Image Synthesis with Cascaded Refinement Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[11]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[12]  Radim Sára,et al.  Spatial Pattern Templates for Recognition of Objects with Regular Structure , 2013, GCPR.

[13]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  Ming-Yu Liu,et al.  Coupled Generative Adversarial Networks , 2016, NIPS.

[15]  David Lopez-Paz,et al.  Optimizing the Latent Space of Generative Networks , 2017, ICML.

[16]  Thomas Brox,et al.  Generating Images with Perceptual Similarity Metrics based on Deep Networks , 2016, NIPS.

[17]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[18]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Heng Tao Shen,et al.  Unpaired Image-to-Image Translation from Shared Deep Space , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[20]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[21]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[22]  Yang Song,et al.  Learning Fine-Grained Image Similarity with Deep Ranking , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.