NAM: Non-Adversarial Unsupervised Domain Mapping

Hoshen, Yedid; Lior, Wolf

doi:10.48550/arxiv.1806.00804

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A very different recent approach is NAM [5], which relies on having a high quality pre-trained unsupervised generative model for the source domain. If such a generator is available, a generative model needs to be trained only once per target dataset, and can thus be used to map to many target domains without adversarial generative training.…”

Section: Related Workmentioning

confidence: 99%

“…From top to bottom, we show image-to-image translation results for: Apples ↔ Oranges and Summer ↔ Winter images. All of our results were achieved with the full loss in (5), with the relative weights reported in Section 3.5. Qualitatively, it may be observed that in all three image-toimage translation tasks, CrossNet outperforms CycleGAN, providing better texture transfer, color reproduction, and also better structure (visible in the Apples ↔ Oranges translations).…”

Section: Unpaired Image-to-image Translationmentioning

confidence: 99%

See 1 more Smart Citation

CrossNet: Latent Cross-Consistency for Unpaired Image Translation

Sendik¹,

Lischinski²,

Cohen–Or³

2019

Preprint

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Unpaired Image-to-image Translationmentioning

confidence: 99%

CrossNet: Latent Cross-Consistency for Unpaired Image Translation

Sendik¹,

Lischinski²,

Cohen–Or³

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…There has been a series of non-adversarial approaches to learning domain mappings. (Hoshen and Wolf [2018], Long et al [2015], , , Haeusser et al [2017]). However, all the aforementioned methods focus on the problem of large amounts of unlabelled data in the target domain.…”

Section: Introductionmentioning

confidence: 99%

LRS-DAG: Low Resource Supervised Domain Adaptation with Generalization Across Domains

Uppaal

2019

Preprint

View full text Add to dashboard Cite

Current state of the art methods in Domain Adaptation follow adversarial approaches, making training a challenge. Existing non-adversarial methods learn mappings between the source and target domains, to achieve reasonable performance. However, even these methods do not focus on a key aspect: maintaining performance on the source domain, even after optimizing over the target domain. Additionally, there exist very few methods in low resource supervised domain adaptation. This work proposes a method, LRS-DAG, that aims to solve these current issues in the field. By adding a set of "encoder layers" which map the target domain to the source, and can be removed when dealing directly with the source data, the model learns to perform optimally on both domains. LRS-DAG showcases its uniqueness by being a new algorithm for low resource domain adaptaion which maintains performance over the source domain, with a new metric for learning mappings between domains being introduced. We show that, in the case of FCNs, when transferring from MNIST to SVHN, LRS-DAG performs comparably to fine tuning, with the advantage of maintaining performance over the source domain. LRS-DAG outperforms fine tuning when transferring to a synthetic dataset similar to MNIST, which is a setting more representative of low resource supervised domain adaptation.

show abstract

NAM: Non-Adversarial Unsupervised Domain Mapping

Cited by 2 publications

References 0 publications

CrossNet: Latent Cross-Consistency for Unpaired Image Translation

CrossNet: Latent Cross-Consistency for Unpaired Image Translation

LRS-DAG: Low Resource Supervised Domain Adaptation with Generalization Across Domains

Contact Info

Product

Resources

About