Spatial Alignment for Unsupervised Domain Adaptive Single-Stage Object Detection

Domain adaptation methods are proposed to improve the performance of object detection in new domains without additional annotation costs. Recently, domain adaptation methods based on adversarial learning to align source and target domain image distributions are effective. However, for object detecti...

Descripción completa

Detalles Bibliográficos
Autores principales: Liang, Hong, Tong, Yanqi, Zhang, Qian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9102984/
https://www.ncbi.nlm.nih.gov/pubmed/35590943
http://dx.doi.org/10.3390/s22093253

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9102984/
https://www.ncbi.nlm.nih.gov/pubmed/35590943
http://dx.doi.org/10.3390/s22093253

Ejemplares similares