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...

Deskribapen osoa

Gorde:
Xehetasun bibliografikoak
Egile Nagusiak: Hong Liang, Yanqi Tong, Qian Zhang
Formatua: Artigo
Hizkuntza:Inglês
Argitaratua: MDPI AG 2022-04-01
Saila:Sensors
Gaiak:
domain adaptation
object detection
transfer learning
Sarrera elektronikoa:https://www.mdpi.com/1424-8220/22/9/3253
Etiketak: Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!

Antzeko izenburuak