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...

Full beskrivning

Sparad:
Bibliografiska uppgifter
Huvudupphovsmän: Hong Liang, Yanqi Tong, Qian Zhang
Materialtyp: Artigo
Språk:Inglês
Publicerad: MDPI AG 2022-04-01
Serie:Sensors
Ämnen:
domain adaptation
object detection
transfer learning
Länkar:https://www.mdpi.com/1424-8220/22/9/3253
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!

Liknande verk