NAM - Unsupervised cross-domain image mapping without cycles or GANs

نتاج البحث: نتاج بحثي من مؤتمرمحاضرةمراجعة النظراء

ملخص

Several methods were recently proposed for Unsupervised Domain Mapping, which is the task of translating images between domains without prior knowledge of correspondences. Current approaches suffer from an instability in training due to relying on GANs which are powerful but highly sensitive to hyper-parameters and suffer from mode collapse. In addition, most methods rely heavily on “cycle” relationships between the domains, which enforce a one-to-one mapping. In this work, we introduce an alternative method: NAM. NAM relies on a pre-trained generative model of the source domain, and aligns each target image with an image sampled from the source distribution while jointly optimizing the domain mapping function. Experiments are presented validating the effectiveness of our method.

اللغة الأصليةإنجليزيّة أمريكيّة
حالة النشرنُشِر - 2018
الحدث6th International Conference on Learning Representations, ICLR 2018 - Vancouver, كندا
المدة: ٣٠ أبريل ٢٠١٨٣ مايو ٢٠١٨

!!Conference

!!Conference6th International Conference on Learning Representations, ICLR 2018
الدولة/الإقليمكندا
المدينةVancouver
المدة٣٠/٠٤/١٨٣/٠٥/١٨

All Science Journal Classification (ASJC) codes

  • !!Education
  • !!Computer Science Applications
  • !!Linguistics and Language
  • !!Language and Linguistics

بصمة

أدرس بدقة موضوعات البحث “NAM - Unsupervised cross-domain image mapping without cycles or GANs'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا