It is well-known that GANs are difficult to train, and several different techniques have been proposed in order to stabilize their training. In this paper, we propose a novel training method called manifold-matching, and a new GAN model called manifold-matching GAN (MMGAN). MMGAN finds two manifolds representing the vector representations of real and fake images. If these two manifolds match, it means that real and fake images are statistically identical. To assist the manifold-matching task, we also use i) kernel tricks to find better manifold structures, ii) moving-averaged manifolds across mini-batches, and iii) a regularizer based on correlation matrix to suppress mode collapse. We conduct in-depth experiments with three image datasets and compare with several state-of-the-art GAN models. 32.4% of images generated by the proposed MMGAN are recognized as fake images during our user study (16% enhancement compared to other state-of-the-art model). MMGAN achieved an unsupervised inception score of 7.8 for CIFAR-10.
|Title of host publication||2018 24th International Conference on Pattern Recognition, ICPR 2018|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||6|
|Publication status||Published - 2018 Nov 26|
|Event||24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China|
Duration: 2018 Aug 20 → 2018 Aug 24
|Name||Proceedings - International Conference on Pattern Recognition|
|Other||24th International Conference on Pattern Recognition, ICPR 2018|
|Period||18/8/20 → 18/8/24|
Bibliographical noteFunding Information:
This work was supported by the National Research Council of Science & Technology (NST) grant by the Korea government (MSIP) [No. CRC-15-05-ETRI].
© 2018 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition