Learning efficient text-to-image synthesis via interstage cross-sample similarity distillation

Fengling Mao, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen

Abstract

For a given text, previous text-to-image synthesis methods commonly utilize a multistage generation model to produce images with high resolution in a coarse-to-fine manner. However, these methods ignore the interaction among stages, and they do not constrain the consistent cross-sample relations of images generated in different stages. These deficiencies result in inefficient generation and discrimination. In this study, we propose an interstage cross-sample similarity distillation model based on a generative adversarial network (GAN) for learning efficient text-to-image synthesis. To strengthen the interaction among stages, we achieve interstage knowledge distillation from the refined stage to the coarse stages with novel interstage cross-sample similarity distillation blocks. To enhance the constraint on the cross-sample relations of the images generated at different stages, we conduct cross-sample similarity distillation among the stages. Extensive experiments on the Oxford-102 and Caltech-UCSD Birds-200–2011 (CUB) datasets show that our model generates visually pleasing images and achieves quantitatively comparable performance with state-of-the-art methods.
BibTeX
@article{mao2021learning,
  author = {Fengling Mao and Bingpeng Ma and Hong Chang and Shiguang Shan and Xilin Chen},
  title = {{Learning efficient text-to-image synthesis via interstage cross-sample similarity distillation}},
  journal = {Science China Information Sciences},
  year = {2021},
  doi = {10.1007/s11432-020-2900-x},
}

Loading related content...

Figure