English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

A Novel BiLevel Paradigm for Image-to-Image Translation

MPS-Authors
/persons/resource/persons203020

Sun,  Qianru
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1904.09028.pdf
(Preprint), 3MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Ma, L., Sun, Q., Schiele, B., & Van Gool, L. (2019). A Novel BiLevel Paradigm for Image-to-Image Translation. Retrieved from http://arxiv.org/abs/1904.09028.


Cite as: http://hdl.handle.net/21.11116/0000-0003-BB01-9
Abstract
Image-to-image (I2I) translation is a pixel-level mapping that requires a large number of paired training data and often suffers from the problems of high diversity and strong category bias in image scenes. In order to tackle these problems, we propose a novel BiLevel (BiL) learning paradigm that alternates the learning of two models, respectively at an instance-specific (IS) and a general-purpose (GP) level. In each scene, the IS model learns to maintain the specific scene attributes. It is initialized by the GP model that learns from all the scenes to obtain the generalizable translation knowledge. This GP initialization gives the IS model an efficient starting point, thus enabling its fast adaptation to the new scene with scarce training data. We conduct extensive I2I translation experiments on human face and street view datasets. Quantitative results validate that our approach can significantly boost the performance of classical I2I translation models, such as PG2 and Pix2Pix. Our visualization results show both higher image quality and more appropriate instance-specific details, e.g., the translated image of a person looks more like that person in terms of identity.