Diverse Image Generation via Self-Conditioned GANs
Name
2006.10728.pdf
Description
Submitted version
Size
5.24 MB
Format
Adobe PDF
Checksum (MD5)
bf3d32f1f33a602247a0ba761f450a95
Author(s)
Liu, Steven
Wang, Tongzhou
Bau, David
Zhu, Jun-Yan
Torralba, Antonio
Date Issued
2020
Journal
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Liu, Steven, Wang, Tongzhou, Bau, David, Zhu, Jun-Yan and Torralba, Antonio. 2020. "Diverse Image Generation via Self-Conditioned GANs." Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
Version
Original manuscript
Abstract
© 2020 IEEE. We introduce a simple but effective unsupervised method for generating diverse images. We train a class-conditional GAN model without using manually annotated class labels. Instead, our model is conditional on labels automatically derived from clustering in the discriminator's feature space. Our clustering step automatically discovers diverse modes, and explicitly requires the generator to cover them. Experiments on standard mode collapse benchmarks show that our method outperforms several competing methods when addressing mode collapse. Our method also performs well on large-scale datasets such as ImageNet and Places365, improving both diversity and standard metrics (e.g., Fréchet Inception Distance), compared to previous methods.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR42600.2020.01429
