Cycle-Consistent Domain Adaptive Faster RCNN

Cycle-Consistent Domain Adaptive Faster RCNN

Traditional object detection methods always assume both of the training and test data follow the same distribution, but this cannot always be guaranteed in the real world. Domain adaptive methods are proposed to handle this situation. However, existing methods generally ignore the semantic alignment...

Full description

Bibliographic Details
Main Authors: Dan Zhang, Jingjing Li, Lin Xiong, Lan Lin, Mao Ye, Shangming Yang
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Domain adaptive object detection
generative adversarial net
semantic information
Online Access:https://ieeexplore.ieee.org/document/8822427/

Internet

https://ieeexplore.ieee.org/document/8822427/

Similar Items