mathfinder / Cross-domain-Human-Parsing-via-Adversarial-Feature-and-Label-Adaptation

we propose a novel and efficient cross-domain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation net-work, which is specialized for mitigating the cross-domain differences. A…
15Updated 7 years ago

Alternatives and similar repositories for Cross-domain-Human-Parsing-via-Adversarial-Feature-and-Label-Adaptation:

Users that are interested in Cross-domain-Human-Parsing-via-Adversarial-Feature-and-Label-Adaptation are comparing it to the libraries listed below