Method evidence record

CycleGAN

CycleGAN, introduced by Zhu et al. at ICCV 2017, learns to translate images between two visual domains without requiring paired training examples. It trains two generators and two discriminators simultaneously, enforcing a cycle-consistency constraint so that an image translated from domain X to Y and back again recovers the original. This makes it applicable whenever large aligned datasets are unavailable, such as converting photographs to artwork styles, turning summer landscapes into winter scenes, or mapping satellite imagery to map tiles.

Sources recorded, not reviewed

Source record

Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.

CycleGAN (Cycle-Consistent Image Translation)

Taxonomic method record · ml-model / deep-learning

Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. IEEE International Conference on Computer Vision (ICCV), 2242–2251. · DOI 10.1109/ICCV.2017.244

Open full method

Curated claims

Claims persisted in the evidence ledger, each with its own assessment.

No curated claims yet

This view does not invent a claim assessment when the ledger has none.

Related methods

Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.

Same method familyGenerative Adversarial Networkmachine-suggested · Relational suggestion, not evidence.Same method familyNeural Style Transfermachine-suggested · Relational suggestion, not evidence.Taxonomic bucketWasserstein GANmachine-suggested · Relational suggestion, not evidence.