Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment

Jiayu Xiao, Liang Li, Chaofei Wang, Zheng-Jun Zha, Qingming Huang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 11204-11213

Abstract


Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption. However, existing methods are prone to model overfitting and collapse in extremely few shot setting (less than 10). To solve this problem, we propose a relaxed spatial structural alignment (RSSA) method to calibrate the target generative models during the adaption. We design a cross-domain spatial structural consistency loss comprising the self-correlation and disturbance correlation consistency loss. It helps align the spatial structural information between the synthesis image pairs of the source and target domains. To relax the cross-domain alignment, we compress the original latent space of generative models to a subspace. Image pairs generated from the subspace are pulled closer. Qualitative and quantitative experiments show that our method consistently surpasses the state-of-the-art methods in few shot setting. Our source code: https://github.com/StevenShaw1999/RSSA.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Xiao_2022_CVPR, author = {Xiao, Jiayu and Li, Liang and Wang, Chaofei and Zha, Zheng-Jun and Huang, Qingming}, title = {Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {11204-11213} }