Learning To Memorize Feature Hallucination for One-Shot Image Generation

Yu Xie, Yanwei Fu, Ying Tai, Yun Cao, Junwei Zhu, Chengjie Wang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 9130-9139

Abstract


This paper studies the task of One-Shot image Generation (OSG), where generation network learned on base dataset should be generalizable to synthesize images of novel categories with only one available sample per novel category. Most existing methods for feature transfer in one-shot image generation only learn reusable features implicitly on pre-training tasks. Such methods would be likely to overfit pre-training tasks. In this paper, we propose a novel model to explicitly learn and memorize reusable features that can help hallucinate novel category images. To be specific, our algorithm learns to decompose image features into the Category-Related (CR) and Category-Independent (CI) features. Our model learning to memorize class-independent CI features which are further utilized by our feature hallucination component to generate target novel category images. We validate our model on several benchmarks. Extensive experiments demonstrate that our model effectively boosts the OSG performance and can generate compelling and diverse samples.

Related Material


[pdf]
[bibtex]
@InProceedings{Xie_2022_CVPR, author = {Xie, Yu and Fu, Yanwei and Tai, Ying and Cao, Yun and Zhu, Junwei and Wang, Chengjie}, title = {Learning To Memorize Feature Hallucination for One-Shot Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {9130-9139} }