Exploring Unlabeled Faces for Novel Attribute Discovery

Cited 3 time in webofscience Cited 0 time in scopus
  • Hit : 119
  • Download : 0
Despite remarkable success in unpaired image-to-image translation, existing systems still require a large amount of labeled images. This is a bottleneck for their real-world applications; in practice, a model trained on labeled CelebA dataset does not work well for test images from a different distribution - greatly limiting their application to unlabeled images of a much larger quantity. In this paper, we attempt to alleviate this necessity for labeled data in the facial image translation domain. We aim to explore the degree to which you can discover novel attributes from unlabeled faces and perform high-quality translation. To this end, we use prior knowledge about the visual world as guidance to discover novel attributes and transfer them via a novel normalization method. Experiments show that our method trained on unlabeled data produces high-quality translations, preserves identity, and be perceptually realistic, as good as, or better than, state-of-the-art methods trained on labeled data.
Publisher
IEEE Computer Society
Issue Date
2020-06
Language
English
Citation

IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, pp.5820 - 5829

ISSN
1063-6919
DOI
10.1109/CVPR42600.2020.00586
URI
http://hdl.handle.net/10203/278861
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 3 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0